[{"status":"public","external_id":{"isi":["000426219600025"]},"department":[{"_id":"NiBa"},{"_id":"ChLa"}],"isi":1,"publication":"Genetics","article_processing_charge":"No","language":[{"iso":"eng"}],"related_material":{"record":[{"relation":"dissertation_contains","status":"public","id":"200"}]},"date_updated":"2026-04-08T14:06:35Z","month":"03","corr_author":"1","publisher":"Genetics Society of America","issue":"3","publist_id":"7251","day":"01","year":"2018","type":"journal_article","main_file_link":[{"open_access":"1","url":"https://www.biorxiv.org/content/10.1101/205484v1"}],"page":"1231-1245","quality_controlled":"1","abstract":[{"text":"In continuous populations with local migration, nearby pairs of individuals have on average more similar genotypes\r\nthan geographically well separated pairs. A barrier to gene flow distorts this classical pattern of isolation by distance. Genetic similarity is decreased for sample pairs on different sides of the barrier and increased for pairs on the same side near the barrier. Here, we introduce an inference scheme that utilizes this signal to detect and estimate the strength of a linear barrier to gene flow in two-dimensions. We use a diffusion approximation to model the effects of a barrier on the geographical spread of ancestry backwards in time. This approach allows us to calculate the chance of recent coalescence and probability of identity by descent. We introduce an inference scheme that fits these theoretical results to the geographical covariance structure of bialleleic genetic markers. It can estimate the strength of the barrier as well as several demographic parameters. We investigate the power of our inference scheme to detect barriers by applying it to a wide range of simulated data. We also showcase an example application to a Antirrhinum majus (snapdragon) flower color hybrid zone, where we do not detect any signal of a strong genome wide barrier to gene flow.","lang":"eng"}],"title":"Estimating barriers to gene flow from distorted isolation-by-distance patterns","oa_version":"Preprint","publication_status":"published","scopus_import":"1","_id":"563","doi":"10.1534/genetics.117.300638","author":[{"orcid":"0000-0002-4884-9682","last_name":"Ringbauer","first_name":"Harald","id":"417FCFF4-F248-11E8-B48F-1D18A9856A87","full_name":"Ringbauer, Harald"},{"last_name":"Kolesnikov","first_name":"Alexander","id":"2D157DB6-F248-11E8-B48F-1D18A9856A87","full_name":"Kolesnikov, Alexander"},{"full_name":"Field, David","first_name":"David","last_name":"Field"},{"full_name":"Barton, Nicholas H","id":"4880FE40-F248-11E8-B48F-1D18A9856A87","first_name":"Nicholas H","last_name":"Barton","orcid":"0000-0002-8548-5240"}],"date_created":"2018-12-11T11:47:12Z","user_id":"c635000d-4b10-11ee-a964-aac5a93f6ac1","citation":{"apa":"Ringbauer, H., Kolesnikov, A., Field, D., &#38; Barton, N. H. (2018). Estimating barriers to gene flow from distorted isolation-by-distance patterns. <i>Genetics</i>. Genetics Society of America. <a href=\"https://doi.org/10.1534/genetics.117.300638\">https://doi.org/10.1534/genetics.117.300638</a>","ama":"Ringbauer H, Kolesnikov A, Field D, Barton NH. Estimating barriers to gene flow from distorted isolation-by-distance patterns. <i>Genetics</i>. 2018;208(3):1231-1245. doi:<a href=\"https://doi.org/10.1534/genetics.117.300638\">10.1534/genetics.117.300638</a>","short":"H. Ringbauer, A. Kolesnikov, D. Field, N.H. Barton, Genetics 208 (2018) 1231–1245.","mla":"Ringbauer, Harald, et al. “Estimating Barriers to Gene Flow from Distorted Isolation-by-Distance Patterns.” <i>Genetics</i>, vol. 208, no. 3, Genetics Society of America, 2018, pp. 1231–45, doi:<a href=\"https://doi.org/10.1534/genetics.117.300638\">10.1534/genetics.117.300638</a>.","chicago":"Ringbauer, Harald, Alexander Kolesnikov, David Field, and Nicholas H Barton. “Estimating Barriers to Gene Flow from Distorted Isolation-by-Distance Patterns.” <i>Genetics</i>. Genetics Society of America, 2018. <a href=\"https://doi.org/10.1534/genetics.117.300638\">https://doi.org/10.1534/genetics.117.300638</a>.","ieee":"H. Ringbauer, A. Kolesnikov, D. Field, and N. H. Barton, “Estimating barriers to gene flow from distorted isolation-by-distance patterns,” <i>Genetics</i>, vol. 208, no. 3. Genetics Society of America, pp. 1231–1245, 2018.","ista":"Ringbauer H, Kolesnikov A, Field D, Barton NH. 2018. Estimating barriers to gene flow from distorted isolation-by-distance patterns. Genetics. 208(3), 1231–1245."},"date_published":"2018-03-01T00:00:00Z","oa":1,"intvolume":"       208","volume":208},{"_id":"1108","date_created":"2018-12-11T11:50:11Z","author":[{"last_name":"Zimin","first_name":"Alexander","id":"37099E9C-F248-11E8-B48F-1D18A9856A87","full_name":"Zimin, Alexander"},{"last_name":"Lampert","orcid":"0000-0001-8622-7887","first_name":"Christoph","id":"40C20FD2-F248-11E8-B48F-1D18A9856A87","full_name":"Lampert, Christoph"}],"user_id":"2DF688A6-F248-11E8-B48F-1D18A9856A87","citation":{"apa":"Zimin, A., &#38; Lampert, C. (2017). Learning theory for conditional risk minimization (Vol. 54, pp. 213–222). Presented at the AISTATS: Artificial Intelligence and Statistics, Fort Lauderdale, FL, United States: ML Research Press.","ama":"Zimin A, Lampert C. Learning theory for conditional risk minimization. In: Vol 54. ML Research Press; 2017:213-222.","mla":"Zimin, Alexander, and Christoph Lampert. <i>Learning Theory for Conditional Risk Minimization</i>. Vol. 54, ML Research Press, 2017, pp. 213–22.","short":"A. Zimin, C. Lampert, in:, ML Research Press, 2017, pp. 213–222.","chicago":"Zimin, Alexander, and Christoph Lampert. “Learning Theory for Conditional Risk Minimization,” 54:213–22. ML Research Press, 2017.","ieee":"A. Zimin and C. Lampert, “Learning theory for conditional risk minimization,” presented at the AISTATS: Artificial Intelligence and Statistics, Fort Lauderdale, FL, United States, 2017, vol. 54, pp. 213–222.","ista":"Zimin A, Lampert C. 2017. Learning theory for conditional risk minimization. AISTATS: Artificial Intelligence and Statistics, PMLR, vol. 54, 213–222."},"oa":1,"date_published":"2017-04-01T00:00:00Z","intvolume":"        54","alternative_title":["PMLR"],"volume":54,"main_file_link":[{"url":"http://proceedings.mlr.press/v54/zimin17a/zimin17a.pdf","open_access":"1"}],"page":"213 - 222","quality_controlled":"1","abstract":[{"text":"In this work we study the learnability of stochastic processes with respect to the conditional risk, i.e. the existence of a learning algorithm that improves its next-step performance with the amount of observed data. We introduce a notion of pairwise discrepancy between conditional distributions at different times steps and show how certain properties of these discrepancies can be used to construct a successful learning algorithm. Our main results are two theorems that establish criteria for learnability for many classes of stochastic processes, including all special cases studied previously in the literature.","lang":"eng"}],"oa_version":"Submitted Version","title":"Learning theory for conditional risk minimization","publication_status":"published","month":"04","publisher":"ML Research Press","conference":{"location":"Fort Lauderdale, FL, United States","end_date":"2017-04-22","name":"AISTATS: Artificial Intelligence and Statistics","start_date":"2017-04-20"},"day":"01","publist_id":"6261","ec_funded":1,"year":"2017","type":"conference","project":[{"_id":"2532554C-B435-11E9-9278-68D0E5697425","call_identifier":"FP7","name":"Lifelong Learning of Visual Scene Understanding","grant_number":"308036"}],"status":"public","external_id":{"isi":["000509368500024"]},"isi":1,"department":[{"_id":"ChLa"}],"article_processing_charge":"No","language":[{"iso":"eng"}],"date_updated":"2025-04-15T07:10:22Z"},{"year":"2017","type":"conference","project":[{"_id":"2532554C-B435-11E9-9278-68D0E5697425","grant_number":"308036","name":"Lifelong Learning of Visual Scene Understanding","call_identifier":"FP7"}],"ec_funded":1,"day":"01","publist_id":"6398","month":"08","conference":{"location":"Sydney, Australia","name":"ICML: International Conference on Machine Learning","start_date":"2017-08-06","end_date":"2017-08-11"},"publisher":"JMLR","date_updated":"2025-04-15T07:10:22Z","language":[{"iso":"eng"}],"publication":"34th International Conference on Machine Learning","has_accepted_license":"1","isi":1,"department":[{"_id":"ChLa"}],"article_processing_charge":"No","status":"public","external_id":{"arxiv":["1612.08185"],"isi":["000683309501102"]},"publication_identifier":{"isbn":["978-151085514-4"]},"volume":70,"intvolume":"        70","acknowledgement":"We thank Tim Salimans for spotting a mistake in our preliminary arXiv manuscript. This work was funded by the European Research Council under the European Unions Seventh Framework Programme (FP7/2007-2013)/ERC grant agreement no 308036.","user_id":"2DF688A6-F248-11E8-B48F-1D18A9856A87","oa":1,"date_published":"2017-08-01T00:00:00Z","arxiv":1,"citation":{"ama":"Kolesnikov A, Lampert C. PixelCNN models with auxiliary variables for natural image modeling. In: <i>34th International Conference on Machine Learning</i>. Vol 70. JMLR; 2017:1905-1914.","chicago":"Kolesnikov, Alexander, and Christoph Lampert. “PixelCNN Models with Auxiliary Variables for Natural Image Modeling.” In <i>34th International Conference on Machine Learning</i>, 70:1905–14. JMLR, 2017.","short":"A. Kolesnikov, C. Lampert, in:, 34th International Conference on Machine Learning, JMLR, 2017, pp. 1905–1914.","mla":"Kolesnikov, Alexander, and Christoph Lampert. “PixelCNN Models with Auxiliary Variables for Natural Image Modeling.” <i>34th International Conference on Machine Learning</i>, vol. 70, JMLR, 2017, pp. 1905–14.","apa":"Kolesnikov, A., &#38; Lampert, C. (2017). PixelCNN models with auxiliary variables for natural image modeling. In <i>34th International Conference on Machine Learning</i> (Vol. 70, pp. 1905–1914). Sydney, Australia: JMLR.","ista":"Kolesnikov A, Lampert C. 2017. PixelCNN models with auxiliary variables for natural image modeling. 34th International Conference on Machine Learning. ICML: International Conference on Machine Learning vol. 70, 1905–1914.","ieee":"A. Kolesnikov and C. Lampert, “PixelCNN models with auxiliary variables for natural image modeling,” in <i>34th International Conference on Machine Learning</i>, Sydney, Australia, 2017, vol. 70, pp. 1905–1914."},"_id":"1000","scopus_import":"1","date_created":"2018-12-11T11:49:37Z","author":[{"last_name":"Kolesnikov","first_name":"Alexander","id":"2D157DB6-F248-11E8-B48F-1D18A9856A87","full_name":"Kolesnikov, Alexander"},{"full_name":"Lampert, Christoph","id":"40C20FD2-F248-11E8-B48F-1D18A9856A87","first_name":"Christoph","orcid":"0000-0001-8622-7887","last_name":"Lampert"}],"oa_version":"Submitted Version","title":"PixelCNN models with auxiliary variables for natural image modeling","publication_status":"published","abstract":[{"lang":"eng","text":"We study probabilistic models of natural images and extend the autoregressive family of PixelCNN models by incorporating latent variables. Subsequently, we describe two new generative image models that exploit different image transformations as latent variables: a quantized grayscale view of the image or a multi-resolution image pyramid. The proposed models tackle two known shortcomings of existing PixelCNN models: 1) their tendency to focus on low-level image details, while largely ignoring high-level image information, such as object shapes, and 2) their computationally costly procedure for image sampling. We experimentally demonstrate benefits of our LatentPixelCNN models, in particular showing that they produce much more realistically looking image samples than previous state-of-the-art probabilistic models. "}],"quality_controlled":"1","main_file_link":[{"url":"https://arxiv.org/abs/1612.08185","open_access":"1"}],"page":"1905 - 1914"},{"article_number":"7846789","status":"public","quality_controlled":"1","department":[{"_id":"ChLa"},{"_id":"GaTk"}],"language":[{"iso":"eng"}],"abstract":[{"lang":"eng","text":"We present an approach that enables robots to self-organize their sensorimotor behavior from scratch without providing specific information about neither the robot nor its environment. This is achieved by a simple neural control law that increases the consistency between external sensor dynamics and internal neural dynamics of the utterly simple controller. In this way, the embodiment and the agent-environment coupling are the only source of individual development. We show how an anthropomorphic tendon driven arm-shoulder system develops different behaviors depending on that coupling. For instance: Given a bottle half-filled with water, the arm starts to shake it, driven by the physical response of the water. When attaching a brush, the arm can be manipulated into wiping a table, and when connected to a revolvable wheel it finds out how to rotate it. Thus, the robot may be said to discover the affordances of the world. When allowing two (simulated) humanoid robots to interact physically, they engage into a joint behavior development leading to, for instance, spontaneous cooperation. More social effects are observed if the robots can visually perceive each other. Although, as an observer, it is tempting to attribute an apparent intentionality, there is nothing of the kind put in. As a conclusion, we argue that emergent behavior may be much less rooted in explicit intentions, internal motivations, or specific reward systems than is commonly believed."}],"date_updated":"2021-01-12T08:07:51Z","publication_status":"published","oa_version":"None","title":"Dynamical self consistency leads to behavioral development and emergent social interactions in robots","publisher":"IEEE","date_created":"2018-12-11T11:47:43Z","doi":"10.1109/DEVLRN.2016.7846789","conference":{"end_date":"2016-09-22","start_date":"2016-09-19","name":"ICDL EpiRob: International Conference on Development and Learning and Epigenetic Robotics ","location":"Cergy-Pontoise, France"},"author":[{"full_name":"Der, Ralf","first_name":"Ralf","last_name":"Der"},{"full_name":"Martius, Georg S","id":"3A276B68-F248-11E8-B48F-1D18A9856A87","first_name":"Georg S","last_name":"Martius"}],"scopus_import":1,"month":"02","_id":"652","citation":{"ama":"Der R, Martius GS. Dynamical self consistency leads to behavioral development and emergent social interactions in robots. In: IEEE; 2017. doi:<a href=\"https://doi.org/10.1109/DEVLRN.2016.7846789\">10.1109/DEVLRN.2016.7846789</a>","short":"R. Der, G.S. Martius, in:, IEEE, 2017.","chicago":"Der, Ralf, and Georg S Martius. “Dynamical Self Consistency Leads to Behavioral Development and Emergent Social Interactions in Robots.” IEEE, 2017. <a href=\"https://doi.org/10.1109/DEVLRN.2016.7846789\">https://doi.org/10.1109/DEVLRN.2016.7846789</a>.","mla":"Der, Ralf, and Georg S. Martius. <i>Dynamical Self Consistency Leads to Behavioral Development and Emergent Social Interactions in Robots</i>. 7846789, IEEE, 2017, doi:<a href=\"https://doi.org/10.1109/DEVLRN.2016.7846789\">10.1109/DEVLRN.2016.7846789</a>.","apa":"Der, R., &#38; Martius, G. S. (2017). Dynamical self consistency leads to behavioral development and emergent social interactions in robots. Presented at the ICDL EpiRob: International Conference on Development and Learning and Epigenetic Robotics , Cergy-Pontoise, France: IEEE. <a href=\"https://doi.org/10.1109/DEVLRN.2016.7846789\">https://doi.org/10.1109/DEVLRN.2016.7846789</a>","ista":"Der R, Martius GS. 2017. Dynamical self consistency leads to behavioral development and emergent social interactions in robots. ICDL EpiRob: International Conference on Development and Learning and Epigenetic Robotics , 7846789.","ieee":"R. Der and G. S. Martius, “Dynamical self consistency leads to behavioral development and emergent social interactions in robots,” presented at the ICDL EpiRob: International Conference on Development and Learning and Epigenetic Robotics , Cergy-Pontoise, France, 2017."},"date_published":"2017-02-07T00:00:00Z","user_id":"3E5EF7F0-F248-11E8-B48F-1D18A9856A87","day":"07","publist_id":"7100","type":"conference","year":"2017","publication_identifier":{"isbn":["978-150905069-7"]}},{"ec_funded":1,"tmp":{"name":"Creative Commons Attribution 4.0 International Public License (CC-BY 4.0)","short":"CC BY (4.0)","legal_code_url":"https://creativecommons.org/licenses/by/4.0/legalcode","image":"/images/cc_by.png"},"type":"journal_article","project":[{"name":"International IST Postdoc Fellowship Programme","call_identifier":"FP7","grant_number":"291734","_id":"25681D80-B435-11E9-9278-68D0E5697425"}],"pubrep_id":"903","year":"2017","publisher":"Frontiers Research Foundation","corr_author":"1","month":"03","day":"16","issue":"MAR","publist_id":"7078","language":[{"iso":"eng"}],"ddc":["006"],"file":[{"date_created":"2018-12-12T10:18:49Z","file_id":"5371","checksum":"b1bc43f96d1df3313c03032c2a46388d","file_name":"IST-2017-903-v1+1_fnbot-11-00008.pdf","access_level":"open_access","creator":"system","relation":"main_file","content_type":"application/pdf","file_size":8439566,"date_updated":"2020-07-14T12:47:33Z"}],"date_updated":"2025-09-11T07:10:33Z","external_id":{"isi":["000396303400001"]},"article_number":"00008","status":"public","article_processing_charge":"Yes","publication":"Frontiers in Neurorobotics","has_accepted_license":"1","isi":1,"department":[{"_id":"ChLa"},{"_id":"GaTk"}],"intvolume":"        11","volume":11,"publication_identifier":{"issn":["1662-5218"]},"doi":"10.3389/fnbot.2017.00008","author":[{"full_name":"Der, Ralf","last_name":"Der","first_name":"Ralf"},{"first_name":"Georg S","last_name":"Martius","full_name":"Martius, Georg S","id":"3A276B68-F248-11E8-B48F-1D18A9856A87"}],"date_created":"2018-12-11T11:47:45Z","_id":"658","scopus_import":"1","oa":1,"date_published":"2017-03-16T00:00:00Z","citation":{"apa":"Der, R., &#38; Martius, G. S. (2017). Self organized behavior generation for musculoskeletal robots. <i>Frontiers in Neurorobotics</i>. Frontiers Research Foundation. <a href=\"https://doi.org/10.3389/fnbot.2017.00008\">https://doi.org/10.3389/fnbot.2017.00008</a>","ama":"Der R, Martius GS. Self organized behavior generation for musculoskeletal robots. <i>Frontiers in Neurorobotics</i>. 2017;11(MAR). doi:<a href=\"https://doi.org/10.3389/fnbot.2017.00008\">10.3389/fnbot.2017.00008</a>","mla":"Der, Ralf, and Georg S. Martius. “Self Organized Behavior Generation for Musculoskeletal Robots.” <i>Frontiers in Neurorobotics</i>, vol. 11, no. MAR, 00008, Frontiers Research Foundation, 2017, doi:<a href=\"https://doi.org/10.3389/fnbot.2017.00008\">10.3389/fnbot.2017.00008</a>.","short":"R. Der, G.S. Martius, Frontiers in Neurorobotics 11 (2017).","chicago":"Der, Ralf, and Georg S Martius. “Self Organized Behavior Generation for Musculoskeletal Robots.” <i>Frontiers in Neurorobotics</i>. Frontiers Research Foundation, 2017. <a href=\"https://doi.org/10.3389/fnbot.2017.00008\">https://doi.org/10.3389/fnbot.2017.00008</a>.","ieee":"R. Der and G. S. Martius, “Self organized behavior generation for musculoskeletal robots,” <i>Frontiers in Neurorobotics</i>, vol. 11, no. MAR. Frontiers Research Foundation, 2017.","ista":"Der R, Martius GS. 2017. Self organized behavior generation for musculoskeletal robots. Frontiers in Neurorobotics. 11(MAR), 00008."},"user_id":"317138e5-6ab7-11ef-aa6d-ffef3953e345","abstract":[{"lang":"eng","text":"With the accelerated development of robot technologies, control becomes one of the central themes of research. In traditional approaches, the controller, by its internal functionality, finds appropriate actions on the basis of specific objectives for the task at hand. While very successful in many applications, self-organized control schemes seem to be favored in large complex systems with unknown dynamics or which are difficult to model. Reasons are the expected scalability, robustness, and resilience of self-organizing systems. The paper presents a self-learning neurocontroller based on extrinsic differential plasticity introduced recently, applying it to an anthropomorphic musculoskeletal robot arm with attached objects of unknown physical dynamics. The central finding of the paper is the following effect: by the mere feedback through the internal dynamics of the object, the robot is learning to relate each of the objects with a very specific sensorimotor pattern. Specifically, an attached pendulum pilots the arm into a circular motion, a half-filled bottle produces axis oriented shaking behavior, a wheel is getting rotated, and wiping patterns emerge automatically in a table-plus-brush setting. By these object-specific dynamical patterns, the robot may be said to recognize the object's identity, or in other words, it discovers dynamical affordances of objects. Furthermore, when including hand coordinates obtained from a camera, a dedicated hand-eye coordination self-organizes spontaneously. These phenomena are discussed from a specific dynamical system perspective. Central is the dedicated working regime at the border to instability with its potentially infinite reservoir of (limit cycle) attractors &quot;waiting&quot; to be excited. Besides converging toward one of these attractors, variate behavior is also arising from a self-induced attractor morphing driven by the learning rule. We claim that experimental investigations with this anthropomorphic, self-learning robot not only generate interesting and potentially useful behaviors, but may also help to better understand what subjective human muscle feelings are, how they can be rooted in sensorimotor patterns, and how these concepts may feed back on robotics."}],"publication_status":"published","title":"Self organized behavior generation for musculoskeletal robots","oa_version":"Published Version","file_date_updated":"2020-07-14T12:47:33Z","quality_controlled":"1"},{"year":"2017","project":[{"grant_number":"308036","name":"Lifelong Learning of Visual Scene Understanding","call_identifier":"FP7","_id":"2532554C-B435-11E9-9278-68D0E5697425"}],"type":"conference","ec_funded":1,"day":"21","user_id":"3E5EF7F0-F248-11E8-B48F-1D18A9856A87","date_published":"2017-02-21T00:00:00Z","oa":1,"arxiv":1,"citation":{"apa":"Martius, G. S., &#38; Lampert, C. (2017). Extrapolation and learning equations. In <i>5th International Conference on Learning Representations, ICLR 2017 - Workshop Track Proceedings</i>. Toulon, France: International Conference on Learning Representations.","ama":"Martius GS, Lampert C. Extrapolation and learning equations. In: <i>5th International Conference on Learning Representations, ICLR 2017 - Workshop Track Proceedings</i>. International Conference on Learning Representations; 2017.","mla":"Martius, Georg S., and Christoph Lampert. “Extrapolation and Learning Equations.” <i>5th International Conference on Learning Representations, ICLR 2017 - Workshop Track Proceedings</i>, International Conference on Learning Representations, 2017.","short":"G.S. Martius, C. Lampert, in:, 5th International Conference on Learning Representations, ICLR 2017 - Workshop Track Proceedings, International Conference on Learning Representations, 2017.","chicago":"Martius, Georg S, and Christoph Lampert. “Extrapolation and Learning Equations.” In <i>5th International Conference on Learning Representations, ICLR 2017 - Workshop Track Proceedings</i>. International Conference on Learning Representations, 2017.","ieee":"G. S. Martius and C. Lampert, “Extrapolation and learning equations,” in <i>5th International Conference on Learning Representations, ICLR 2017 - Workshop Track Proceedings</i>, Toulon, France, 2017.","ista":"Martius GS, Lampert C. 2017. Extrapolation and learning equations. 5th International Conference on Learning Representations, ICLR 2017 - Workshop Track Proceedings. ICLR: International Conference on Learning Representations."},"_id":"6841","scopus_import":1,"month":"02","date_created":"2019-09-01T22:01:00Z","conference":{"location":"Toulon, France","end_date":"2017-04-26","start_date":"2017-04-24","name":"ICLR: International Conference on Learning Representations"},"author":[{"full_name":"Martius, Georg S","id":"3A276B68-F248-11E8-B48F-1D18A9856A87","first_name":"Georg S","last_name":"Martius"},{"last_name":"Lampert","orcid":"0000-0001-8622-7887","first_name":"Christoph","id":"40C20FD2-F248-11E8-B48F-1D18A9856A87","full_name":"Lampert, Christoph"}],"publisher":"International Conference on Learning Representations","oa_version":"Preprint","title":"Extrapolation and learning equations","publication_status":"published","date_updated":"2021-01-12T08:09:17Z","abstract":[{"text":"In classical machine learning, regression is treated as a black box process of identifying a suitable function from a hypothesis set without attempting to gain insight into the mechanism connecting inputs and outputs. In the natural sciences, however, finding an interpretable function for a phenomenon is the prime goal as it allows to understand and generalize results. This paper proposes a novel type of function learning network, called equation learner (EQL), that can learn analytical expressions and is able to extrapolate to unseen domains. It is implemented as an end-to-end differentiable feed-forward network and allows for efficient gradient based training. Due to sparsity regularization concise interpretable expressions can be obtained. Often the true underlying source expression is identified.","lang":"eng"}],"language":[{"iso":"eng"}],"publication":"5th International Conference on Learning Representations, ICLR 2017 - Workshop Track Proceedings","department":[{"_id":"ChLa"}],"quality_controlled":"1","status":"public","main_file_link":[{"url":"https://arxiv.org/abs/1610.02995","open_access":"1"}],"external_id":{"arxiv":["1610.02995"]}},{"scopus_import":1,"month":"12","_id":"750","publisher":"IEEE","author":[{"full_name":"Pielorz, Jasmin","id":"49BC895A-F248-11E8-B48F-1D18A9856A87","first_name":"Jasmin","last_name":"Pielorz"},{"full_name":"Prandtstetter, Matthias","first_name":"Matthias","last_name":"Prandtstetter"},{"first_name":"Markus","last_name":"Straub","full_name":"Straub, Markus"},{"id":"40C20FD2-F248-11E8-B48F-1D18A9856A87","full_name":"Lampert, Christoph","orcid":"0000-0001-8622-7887","last_name":"Lampert","first_name":"Christoph"}],"doi":"10.1109/BigData.2017.8258375","conference":{"location":"Boston, MA, United States","start_date":"2017-12-11","name":"Big Data","end_date":"2017-12-14"},"date_created":"2018-12-11T11:48:18Z","user_id":"2DF688A6-F248-11E8-B48F-1D18A9856A87","publist_id":"6906","day":"01","citation":{"ieee":"J. Pielorz, M. Prandtstetter, M. Straub, and C. Lampert, “Optimal geospatial volunteer allocation needs realistic distances,” in <i>2017 IEEE International Conference on Big Data</i>, Boston, MA, United States, 2017, pp. 3760–3763.","ista":"Pielorz J, Prandtstetter M, Straub M, Lampert C. 2017. Optimal geospatial volunteer allocation needs realistic distances. 2017 IEEE International Conference on Big Data. Big Data, 3760–3763.","apa":"Pielorz, J., Prandtstetter, M., Straub, M., &#38; Lampert, C. (2017). Optimal geospatial volunteer allocation needs realistic distances. In <i>2017 IEEE International Conference on Big Data</i> (pp. 3760–3763). Boston, MA, United States: IEEE. <a href=\"https://doi.org/10.1109/BigData.2017.8258375\">https://doi.org/10.1109/BigData.2017.8258375</a>","ama":"Pielorz J, Prandtstetter M, Straub M, Lampert C. Optimal geospatial volunteer allocation needs realistic distances. In: <i>2017 IEEE International Conference on Big Data</i>. IEEE; 2017:3760-3763. doi:<a href=\"https://doi.org/10.1109/BigData.2017.8258375\">10.1109/BigData.2017.8258375</a>","mla":"Pielorz, Jasmin, et al. “Optimal Geospatial Volunteer Allocation Needs Realistic Distances.” <i>2017 IEEE International Conference on Big Data</i>, IEEE, 2017, pp. 3760–63, doi:<a href=\"https://doi.org/10.1109/BigData.2017.8258375\">10.1109/BigData.2017.8258375</a>.","short":"J. Pielorz, M. Prandtstetter, M. Straub, C. Lampert, in:, 2017 IEEE International Conference on Big Data, IEEE, 2017, pp. 3760–3763.","chicago":"Pielorz, Jasmin, Matthias Prandtstetter, Markus Straub, and Christoph Lampert. “Optimal Geospatial Volunteer Allocation Needs Realistic Distances.” In <i>2017 IEEE International Conference on Big Data</i>, 3760–63. IEEE, 2017. <a href=\"https://doi.org/10.1109/BigData.2017.8258375\">https://doi.org/10.1109/BigData.2017.8258375</a>."},"date_published":"2017-12-01T00:00:00Z","year":"2017","publication_identifier":{"isbn":["978-153862714-3"]},"type":"conference","status":"public","page":"3760 - 3763","quality_controlled":"1","department":[{"_id":"ChLa"}],"publication":"2017 IEEE International Conference on Big Data","abstract":[{"lang":"eng","text":"Modern communication technologies allow first responders to contact thousands of potential volunteers simultaneously for support during a crisis or disaster event. However, such volunteer efforts must be well coordinated and monitored, in order to offer an effective relief to the professionals. In this paper we extend earlier work on optimally assigning volunteers to selected landmark locations. In particular, we emphasize the aspect that obtaining good assignments requires not only advanced computational tools, but also a realistic measure of distance between volunteers and landmarks. Specifically, we propose the use of the Open Street Map (OSM) driving distance instead of he previously used flight distance. We find the OSM driving distance to be better aligned with the interests of volunteers and first responders. Furthermore, we show that relying on the flying distance leads to a substantial underestimation of the number of required volunteers, causing negative side effects in case of an actual crisis situation."}],"language":[{"iso":"eng"}],"oa_version":"None","title":"Optimal geospatial volunteer allocation needs realistic distances","date_updated":"2021-01-12T08:13:55Z","publication_status":"published"},{"date_created":"2018-12-11T11:49:37Z","doi":"10.1109/CVPR.2017.587","author":[{"first_name":"Sylvestre Alvise","last_name":"Rebuffi","full_name":"Rebuffi, Sylvestre Alvise"},{"id":"2D157DB6-F248-11E8-B48F-1D18A9856A87","full_name":"Kolesnikov, Alexander","last_name":"Kolesnikov","first_name":"Alexander"},{"full_name":"Sperl, Georg","id":"4DD40360-F248-11E8-B48F-1D18A9856A87","first_name":"Georg","last_name":"Sperl"},{"id":"40C20FD2-F248-11E8-B48F-1D18A9856A87","full_name":"Lampert, Christoph","last_name":"Lampert","orcid":"0000-0001-8622-7887","first_name":"Christoph"}],"_id":"998","scopus_import":"1","date_published":"2017-04-14T00:00:00Z","oa":1,"arxiv":1,"citation":{"apa":"Rebuffi, S. A., Kolesnikov, A., Sperl, G., &#38; Lampert, C. (2017). iCaRL: Incremental classifier and representation learning (Vol. 2017, pp. 5533–5542). Presented at the CVPR: Computer Vision and Pattern Recognition, Honolulu, HA, United States: IEEE. <a href=\"https://doi.org/10.1109/CVPR.2017.587\">https://doi.org/10.1109/CVPR.2017.587</a>","ama":"Rebuffi SA, Kolesnikov A, Sperl G, Lampert C. iCaRL: Incremental classifier and representation learning. In: Vol 2017. IEEE; 2017:5533-5542. doi:<a href=\"https://doi.org/10.1109/CVPR.2017.587\">10.1109/CVPR.2017.587</a>","mla":"Rebuffi, Sylvestre Alvise, et al. <i>ICaRL: Incremental Classifier and Representation Learning</i>. Vol. 2017, IEEE, 2017, pp. 5533–42, doi:<a href=\"https://doi.org/10.1109/CVPR.2017.587\">10.1109/CVPR.2017.587</a>.","short":"S.A. Rebuffi, A. Kolesnikov, G. Sperl, C. Lampert, in:, IEEE, 2017, pp. 5533–5542.","chicago":"Rebuffi, Sylvestre Alvise, Alexander Kolesnikov, Georg Sperl, and Christoph Lampert. “ICaRL: Incremental Classifier and Representation Learning,” 2017:5533–42. IEEE, 2017. <a href=\"https://doi.org/10.1109/CVPR.2017.587\">https://doi.org/10.1109/CVPR.2017.587</a>.","ieee":"S. A. Rebuffi, A. Kolesnikov, G. Sperl, and C. Lampert, “iCaRL: Incremental classifier and representation learning,” presented at the CVPR: Computer Vision and Pattern Recognition, Honolulu, HA, United States, 2017, vol. 2017, pp. 5533–5542.","ista":"Rebuffi SA, Kolesnikov A, Sperl G, Lampert C. 2017. iCaRL: Incremental classifier and representation learning. CVPR: Computer Vision and Pattern Recognition vol. 2017, 5533–5542."},"user_id":"2DF688A6-F248-11E8-B48F-1D18A9856A87","intvolume":"      2017","volume":2017,"publication_identifier":{"isbn":["978-153860457-1"]},"page":"5533 - 5542","main_file_link":[{"url":"https://arxiv.org/abs/1611.07725","open_access":"1"}],"quality_controlled":"1","abstract":[{"lang":"eng","text":"A major open problem on the road to artificial intelligence is the development of incrementally learning systems that learn about more and more concepts over time from a stream of data. In this work, we introduce a new training strategy, iCaRL, that allows learning in such a class-incremental way: only the training data for a small number of classes has to be present at the same time and new classes can be added progressively. iCaRL learns strong classifiers and a data representation simultaneously. This distinguishes it from earlier works that were fundamentally limited to fixed data representations and therefore incompatible with deep learning architectures. We show by experiments on CIFAR-100 and ImageNet ILSVRC 2012 data that iCaRL can learn many classes incrementally over a long period of time where other strategies quickly fail. "}],"publication_status":"published","title":"iCaRL: Incremental classifier and representation learning","oa_version":"Submitted Version","conference":{"location":"Honolulu, HA, United States","name":"CVPR: Computer Vision and Pattern Recognition","start_date":"2017-07-21","end_date":"2017-07-26"},"publisher":"IEEE","month":"04","day":"14","publist_id":"6400","ec_funded":1,"project":[{"_id":"2532554C-B435-11E9-9278-68D0E5697425","call_identifier":"FP7","name":"Lifelong Learning of Visual Scene Understanding","grant_number":"308036"}],"type":"conference","year":"2017","external_id":{"isi":["000418371405066"],"arxiv":["1611.07725"]},"status":"public","article_processing_charge":"No","isi":1,"department":[{"_id":"ChLa"},{"_id":"ChWo"}],"language":[{"iso":"eng"}],"date_updated":"2025-06-04T08:18:32Z"},{"intvolume":"        70","alternative_title":["PMLR"],"volume":70,"publication_identifier":{"isbn":["9781510855144"]},"date_created":"2018-12-11T11:49:37Z","author":[{"first_name":"Anastasia","last_name":"Pentina","full_name":"Pentina, Anastasia","id":"42E87FC6-F248-11E8-B48F-1D18A9856A87"},{"id":"40C20FD2-F248-11E8-B48F-1D18A9856A87","full_name":"Lampert, Christoph","last_name":"Lampert","orcid":"0000-0001-8622-7887","first_name":"Christoph"}],"scopus_import":"1","_id":"999","arxiv":1,"citation":{"ista":"Pentina A, Lampert C. 2017. Multi-task learning with labeled and unlabeled tasks. ICML: International Conference on Machine Learning, PMLR, vol. 70, 2807–2816.","ieee":"A. Pentina and C. Lampert, “Multi-task learning with labeled and unlabeled tasks,” presented at the ICML: International Conference on Machine Learning, Sydney, Australia, 2017, vol. 70, pp. 2807–2816.","ama":"Pentina A, Lampert C. Multi-task learning with labeled and unlabeled tasks. In: Vol 70. ML Research Press; 2017:2807-2816.","short":"A. Pentina, C. Lampert, in:, ML Research Press, 2017, pp. 2807–2816.","chicago":"Pentina, Anastasia, and Christoph Lampert. “Multi-Task Learning with Labeled and Unlabeled Tasks,” 70:2807–16. ML Research Press, 2017.","mla":"Pentina, Anastasia, and Christoph Lampert. <i>Multi-Task Learning with Labeled and Unlabeled Tasks</i>. Vol. 70, ML Research Press, 2017, pp. 2807–16.","apa":"Pentina, A., &#38; Lampert, C. (2017). Multi-task learning with labeled and unlabeled tasks (Vol. 70, pp. 2807–2816). Presented at the ICML: International Conference on Machine Learning, Sydney, Australia: ML Research Press."},"date_published":"2017-06-08T00:00:00Z","oa":1,"user_id":"2DF688A6-F248-11E8-B48F-1D18A9856A87","abstract":[{"text":"In multi-task learning, a learner is given a collection of prediction tasks and needs to solve all of them. In contrast to previous work, which required that annotated training data must be available for all tasks, we consider a new setting, in which for some tasks, potentially most of them, only unlabeled training data is provided. Consequently, to solve all tasks, information must be transferred between tasks with labels and tasks without labels. Focusing on an instance-based transfer method we analyze two variants of this setting: when the set of labeled tasks is fixed, and when it can be actively selected by the learner. We state and prove a generalization bound that covers both scenarios and derive from it an algorithm for making the choice of labeled tasks (in the active case) and for transferring information between the tasks in a principled way. We also illustrate the effectiveness of the algorithm on synthetic and real data. ","lang":"eng"}],"publication_status":"published","title":"Multi-task learning with labeled and unlabeled tasks","oa_version":"Submitted Version","page":"2807 - 2816","main_file_link":[{"open_access":"1","url":"https://arxiv.org/abs/1602.06518"}],"quality_controlled":"1","ec_funded":1,"type":"conference","project":[{"_id":"2532554C-B435-11E9-9278-68D0E5697425","call_identifier":"FP7","name":"Lifelong Learning of Visual Scene Understanding","grant_number":"308036"}],"year":"2017","publisher":"ML Research Press","conference":{"end_date":"2017-08-11","start_date":"2017-08-06","name":"ICML: International Conference on Machine Learning","location":"Sydney, Australia"},"month":"06","corr_author":"1","day":"08","publist_id":"6399","language":[{"iso":"eng"}],"date_updated":"2025-06-04T08:19:03Z","external_id":{"isi":["000683309502093"],"arxiv":["1602.06518"]},"status":"public","article_processing_charge":"No","department":[{"_id":"ChLa"}],"isi":1},{"day":"01","publist_id":"6532","conference":{"location":"London, United Kingdom","end_date":"2017-09-07","name":"BMVC: British Machine Vision Conference","start_date":"2017-09-04"},"publisher":"BMVA Press","corr_author":"1","month":"09","type":"conference","project":[{"name":"Lifelong Learning of Visual Scene Understanding","call_identifier":"FP7","grant_number":"308036","_id":"2532554C-B435-11E9-9278-68D0E5697425"}],"year":"2017","ec_funded":1,"article_processing_charge":"No","department":[{"_id":"ChLa"}],"has_accepted_license":"1","external_id":{"arxiv":["1705.04258"]},"status":"public","ddc":["000"],"date_updated":"2026-04-08T07:26:44Z","file":[{"access_level":"open_access","creator":"dernst","date_created":"2020-08-10T07:14:33Z","file_id":"8224","file_name":"2017_BMVC_Royer.pdf","relation":"main_file","success":1,"content_type":"application/pdf","file_size":1625363,"date_updated":"2020-08-10T07:14:33Z"}],"related_material":{"record":[{"relation":"dissertation_contains","id":"8390","status":"public"}]},"language":[{"iso":"eng"}],"oa":1,"date_published":"2017-09-01T00:00:00Z","arxiv":1,"citation":{"apa":"Royer, A., Kolesnikov, A., &#38; Lampert, C. (2017). Probabilistic image colorization (p. 85.1-85.12). Presented at the BMVC: British Machine Vision Conference, London, United Kingdom: BMVA Press. <a href=\"https://doi.org/10.5244/c.31.85\">https://doi.org/10.5244/c.31.85</a>","ama":"Royer A, Kolesnikov A, Lampert C. Probabilistic image colorization. In: BMVA Press; 2017:85.1-85.12. doi:<a href=\"https://doi.org/10.5244/c.31.85\">10.5244/c.31.85</a>","mla":"Royer, Amélie, et al. <i>Probabilistic Image Colorization</i>. BMVA Press, 2017, p. 85.1-85.12, doi:<a href=\"https://doi.org/10.5244/c.31.85\">10.5244/c.31.85</a>.","chicago":"Royer, Amélie, Alexander Kolesnikov, and Christoph Lampert. “Probabilistic Image Colorization,” 85.1-85.12. BMVA Press, 2017. <a href=\"https://doi.org/10.5244/c.31.85\">https://doi.org/10.5244/c.31.85</a>.","short":"A. Royer, A. Kolesnikov, C. Lampert, in:, BMVA Press, 2017, p. 85.1-85.12.","ieee":"A. Royer, A. Kolesnikov, and C. Lampert, “Probabilistic image colorization,” presented at the BMVC: British Machine Vision Conference, London, United Kingdom, 2017, p. 85.1-85.12.","ista":"Royer A, Kolesnikov A, Lampert C. 2017. Probabilistic image colorization. BMVC: British Machine Vision Conference, 85.1-85.12."},"user_id":"2DF688A6-F248-11E8-B48F-1D18A9856A87","author":[{"first_name":"Amélie","last_name":"Royer","orcid":"0000-0002-8407-0705","full_name":"Royer, Amélie","id":"3811D890-F248-11E8-B48F-1D18A9856A87"},{"id":"2D157DB6-F248-11E8-B48F-1D18A9856A87","full_name":"Kolesnikov, Alexander","last_name":"Kolesnikov","first_name":"Alexander"},{"full_name":"Lampert, Christoph","id":"40C20FD2-F248-11E8-B48F-1D18A9856A87","first_name":"Christoph","last_name":"Lampert","orcid":"0000-0001-8622-7887"}],"date_created":"2018-12-11T11:49:09Z","doi":"10.5244/c.31.85","_id":"911","scopus_import":"1","publication_identifier":{"eisbn":["190172560X"]},"quality_controlled":"1","file_date_updated":"2020-08-10T07:14:33Z","page":"85.1-85.12","publication_status":"published","title":"Probabilistic image colorization","oa_version":"Published Version","abstract":[{"text":"We develop a probabilistic technique for colorizing grayscale natural images. In light of the intrinsic uncertainty of this task, the proposed probabilistic framework has numerous desirable properties. In particular, our model is able to produce multiple plausible and vivid colorizations for a given grayscale image and is one of the first colorization models to provide a proper stochastic sampling scheme. Moreover, our training procedure is supported by a rigorous theoretical framework that does not require any ad hoc heuristics and allows for efficient modeling and learning of the joint pixel color distribution.We demonstrate strong quantitative and qualitative experimental results on the CIFAR-10 dataset and the challenging ILSVRC 2012 dataset.","lang":"eng"}]},{"department":[{"_id":"ChLa"},{"_id":"GaTk"}],"quality_controlled":"1","status":"public","article_number":"7759138","title":"Compliant control for soft robots: Emergent behavior of a tendon driven anthropomorphic arm","oa_version":"None","date_updated":"2021-01-12T06:49:08Z","publication_status":"published","abstract":[{"lang":"eng","text":"With the accelerated development of robot technologies, optimal control becomes one of the central themes of research. In traditional approaches, the controller, by its internal functionality, finds appropriate actions on the basis of the history of sensor values, guided by the goals, intentions, objectives, learning schemes, and so forth. While very successful with classical robots, these methods run into severe difficulties when applied to soft robots, a new field of robotics with large interest for human-robot interaction. We claim that a novel controller paradigm opens new perspective for this field. This paper applies a recently developed neuro controller with differential extrinsic synaptic plasticity to a muscle-tendon driven arm-shoulder system from the Myorobotics toolkit. In the experiments, we observe a vast variety of self-organized behavior patterns: when left alone, the arm realizes pseudo-random sequences of different poses. By applying physical forces, the system can be entrained into definite motion patterns like wiping a table. Most interestingly, after attaching an object, the controller gets in a functional resonance with the object's internal dynamics, starting to shake spontaneously bottles half-filled with water or sensitively driving an attached pendulum into a circular mode. When attached to the crank of a wheel the neural system independently develops to rotate it. In this way, the robot discovers affordances of objects its body is interacting with."}],"language":[{"iso":"eng"}],"publist_id":"6121","day":"28","user_id":"3E5EF7F0-F248-11E8-B48F-1D18A9856A87","date_published":"2016-11-28T00:00:00Z","citation":{"apa":"Martius, G. S., Hostettler, R., Knoll, A., &#38; Der, R. (2016). Compliant control for soft robots: Emergent behavior of a tendon driven anthropomorphic arm (Vol. 2016–November). Presented at the IEEE RSJ International Conference on Intelligent Robots and Systems IROS , Daejeon, Korea: IEEE. <a href=\"https://doi.org/10.1109/IROS.2016.7759138\">https://doi.org/10.1109/IROS.2016.7759138</a>","ama":"Martius GS, Hostettler R, Knoll A, Der R. Compliant control for soft robots: Emergent behavior of a tendon driven anthropomorphic arm. In: Vol 2016-November. IEEE; 2016. doi:<a href=\"https://doi.org/10.1109/IROS.2016.7759138\">10.1109/IROS.2016.7759138</a>","chicago":"Martius, Georg S, Raphael Hostettler, Alois Knoll, and Ralf Der. “Compliant Control for Soft Robots: Emergent Behavior of a Tendon Driven Anthropomorphic Arm,” Vol. 2016–November. IEEE, 2016. <a href=\"https://doi.org/10.1109/IROS.2016.7759138\">https://doi.org/10.1109/IROS.2016.7759138</a>.","short":"G.S. Martius, R. Hostettler, A. Knoll, R. Der, in:, IEEE, 2016.","mla":"Martius, Georg S., et al. <i>Compliant Control for Soft Robots: Emergent Behavior of a Tendon Driven Anthropomorphic Arm</i>. Vol. 2016–November, 7759138, IEEE, 2016, doi:<a href=\"https://doi.org/10.1109/IROS.2016.7759138\">10.1109/IROS.2016.7759138</a>.","ieee":"G. S. Martius, R. Hostettler, A. Knoll, and R. Der, “Compliant control for soft robots: Emergent behavior of a tendon driven anthropomorphic arm,” presented at the IEEE RSJ International Conference on Intelligent Robots and Systems IROS , Daejeon, Korea, 2016, vol. 2016–November.","ista":"Martius GS, Hostettler R, Knoll A, Der R. 2016. Compliant control for soft robots: Emergent behavior of a tendon driven anthropomorphic arm. IEEE RSJ International Conference on Intelligent Robots and Systems IROS  vol. 2016–November, 7759138."},"_id":"1214","month":"11","scopus_import":1,"author":[{"full_name":"Martius, Georg S","id":"3A276B68-F248-11E8-B48F-1D18A9856A87","first_name":"Georg S","last_name":"Martius"},{"full_name":"Hostettler, Raphael","first_name":"Raphael","last_name":"Hostettler"},{"full_name":"Knoll, Alois","first_name":"Alois","last_name":"Knoll"},{"full_name":"Der, Ralf","first_name":"Ralf","last_name":"Der"}],"date_created":"2018-12-11T11:50:45Z","conference":{"start_date":"2016-09-09","name":"IEEE RSJ International Conference on Intelligent Robots and Systems IROS ","end_date":"2016-09-14","location":"Daejeon, Korea"},"doi":"10.1109/IROS.2016.7759138","publisher":"IEEE","volume":"2016-November","year":"2016","type":"conference","acknowledgement":"RD thanks for the hospitality at the Max-Planck-Institute and for helpful discussions with Nihat Ay and Keyan Zahedi."},{"status":"public","external_id":{"arxiv":["1603.06098"],"isi":["000389385100042"]},"isi":1,"department":[{"_id":"ChLa"}],"article_processing_charge":"No","language":[{"iso":"eng"}],"date_updated":"2025-09-22T07:39:37Z","corr_author":"1","month":"09","conference":{"start_date":"2016-10-11","name":"ECCV: European Conference on Computer Vision","end_date":"2016-10-14","location":"Amsterdam, The Netherlands"},"publisher":"Springer","publist_id":"5842","day":"15","ec_funded":1,"year":"2016","type":"conference","project":[{"grant_number":"308036","call_identifier":"FP7","name":"Lifelong Learning of Visual Scene Understanding","_id":"2532554C-B435-11E9-9278-68D0E5697425"}],"main_file_link":[{"url":"https://arxiv.org/abs/1603.06098","open_access":"1"}],"page":"695 - 711","quality_controlled":"1","abstract":[{"lang":"eng","text":"We introduce a new loss function for the weakly-supervised training of semantic image segmentation models based on three guiding principles: to seed with weak localization cues, to expand objects based on the information about which classes can occur in an image, and to constrain the segmentations to coincide with object boundaries. We show experimentally that training a deep convolutional neural network using the proposed loss function leads to substantially better segmentations than previous state-of-the-art methods on the challenging PASCAL VOC 2012 dataset. We furthermore give insight into the working mechanism of our method by a detailed experimental study that illustrates how the segmentation quality is affected by each term of the proposed loss function as well as their combinations."}],"title":"Seed, expand and constrain: Three principles for weakly-supervised image segmentation","oa_version":"Preprint","publication_status":"published","_id":"1369","scopus_import":"1","author":[{"last_name":"Kolesnikov","first_name":"Alexander","id":"2D157DB6-F248-11E8-B48F-1D18A9856A87","full_name":"Kolesnikov, Alexander"},{"id":"40C20FD2-F248-11E8-B48F-1D18A9856A87","full_name":"Lampert, Christoph","orcid":"0000-0001-8622-7887","last_name":"Lampert","first_name":"Christoph"}],"date_created":"2018-12-11T11:51:37Z","doi":"10.1007/978-3-319-46493-0_42","user_id":"317138e5-6ab7-11ef-aa6d-ffef3953e345","oa":1,"date_published":"2016-09-15T00:00:00Z","arxiv":1,"citation":{"ista":"Kolesnikov A, Lampert C. 2016. Seed, expand and constrain: Three principles for weakly-supervised image segmentation. ECCV: European Conference on Computer Vision, LNCS, vol. 9908, 695–711.","ieee":"A. Kolesnikov and C. Lampert, “Seed, expand and constrain: Three principles for weakly-supervised image segmentation,” presented at the ECCV: European Conference on Computer Vision, Amsterdam, The Netherlands, 2016, vol. 9908, pp. 695–711.","ama":"Kolesnikov A, Lampert C. Seed, expand and constrain: Three principles for weakly-supervised image segmentation. In: Vol 9908. Springer; 2016:695-711. doi:<a href=\"https://doi.org/10.1007/978-3-319-46493-0_42\">10.1007/978-3-319-46493-0_42</a>","short":"A. Kolesnikov, C. Lampert, in:, Springer, 2016, pp. 695–711.","chicago":"Kolesnikov, Alexander, and Christoph Lampert. “Seed, Expand and Constrain: Three Principles for Weakly-Supervised Image Segmentation,” 9908:695–711. Springer, 2016. <a href=\"https://doi.org/10.1007/978-3-319-46493-0_42\">https://doi.org/10.1007/978-3-319-46493-0_42</a>.","mla":"Kolesnikov, Alexander, and Christoph Lampert. <i>Seed, Expand and Constrain: Three Principles for Weakly-Supervised Image Segmentation</i>. Vol. 9908, Springer, 2016, pp. 695–711, doi:<a href=\"https://doi.org/10.1007/978-3-319-46493-0_42\">10.1007/978-3-319-46493-0_42</a>.","apa":"Kolesnikov, A., &#38; Lampert, C. (2016). Seed, expand and constrain: Three principles for weakly-supervised image segmentation (Vol. 9908, pp. 695–711). Presented at the ECCV: European Conference on Computer Vision, Amsterdam, The Netherlands: Springer. <a href=\"https://doi.org/10.1007/978-3-319-46493-0_42\">https://doi.org/10.1007/978-3-319-46493-0_42</a>"},"intvolume":"      9908","volume":9908,"alternative_title":["LNCS"]},{"date_updated":"2025-09-23T10:53:13Z","publication_status":"published","oa_version":"None","title":"Learning Using Privileged Information","language":[{"iso":"eng"}],"abstract":[{"text":"When applying machine learning techniques to real-world problems, prior knowledge plays a crucial role in enriching the learning system. This prior knowledge is typically defined by domain experts and can be integrated into machine learning algorithms in a variety of ways: as a preference of certain prediction functions over others, as a Bayesian prior over parameters, or as additional information about the samples in the training set used for learning a prediction function. The latter setup is called learning using privileged information (LUPI) and was adopted by Vapnik and Vashist in (Neural Netw, 2009). Formally, LUPI refers to the setting when, in addition to the main data modality, the learning system has access to an extra source of information about the training examples. The additional source of information is only available during training and therefore is called privileged. The main goal of LUPI is to utilize privileged information and to learn a better model in the main data modality than one would learn without the privileged source. As an illustration, for protein classification based on amino-acid sequences, the protein tertiary structure can be considered additional information. Another example is recognizing objects in images; the textual information in the form of image tags contains additional object descriptions and can be used as privileged.","lang":"eng"}],"article_processing_charge":"No","quality_controlled":"1","department":[{"_id":"ChLa"}],"publication":"Encyclopedia of Machine Learning and Data Mining","page":"1-4","status":"public","type":"book_chapter","year":"2016","publication_identifier":{"eisbn":["9781489975027"]},"citation":{"ista":"Sharmanska V, Quadrianto N. 2016.Learning Using Privileged Information. In: Encyclopedia of Machine Learning and Data Mining. , 1–4.","ieee":"V. Sharmanska and N. Quadrianto, “Learning Using Privileged Information,” in <i>Encyclopedia of Machine Learning and Data Mining</i>, Springer Nature, 2016, pp. 1–4.","ama":"Sharmanska V, Quadrianto N. Learning Using Privileged Information. In: <i>Encyclopedia of Machine Learning and Data Mining</i>. Springer Nature; 2016:1-4. doi:<a href=\"https://doi.org/10.1007/978-1-4899-7502-7_892-1\">10.1007/978-1-4899-7502-7_892-1</a>","chicago":"Sharmanska, Viktoriia, and Novi Quadrianto. “Learning Using Privileged Information.” In <i>Encyclopedia of Machine Learning and Data Mining</i>, 1–4. Springer Nature, 2016. <a href=\"https://doi.org/10.1007/978-1-4899-7502-7_892-1\">https://doi.org/10.1007/978-1-4899-7502-7_892-1</a>.","mla":"Sharmanska, Viktoriia, and Novi Quadrianto. “Learning Using Privileged Information.” <i>Encyclopedia of Machine Learning and Data Mining</i>, Springer Nature, 2016, pp. 1–4, doi:<a href=\"https://doi.org/10.1007/978-1-4899-7502-7_892-1\">10.1007/978-1-4899-7502-7_892-1</a>.","short":"V. Sharmanska, N. Quadrianto, in:, Encyclopedia of Machine Learning and Data Mining, Springer Nature, 2016, pp. 1–4.","apa":"Sharmanska, V., &#38; Quadrianto, N. (2016). Learning Using Privileged Information. In <i>Encyclopedia of Machine Learning and Data Mining</i> (pp. 1–4). Springer Nature. <a href=\"https://doi.org/10.1007/978-1-4899-7502-7_892-1\">https://doi.org/10.1007/978-1-4899-7502-7_892-1</a>"},"date_published":"2016-07-06T00:00:00Z","OA_type":"closed access","user_id":"2DF688A6-F248-11E8-B48F-1D18A9856A87","day":"06","publisher":"Springer Nature","doi":"10.1007/978-1-4899-7502-7_892-1","author":[{"orcid":"0000-0003-0192-9308","last_name":"Sharmanska","first_name":"Viktoriia","id":"2EA6D09E-F248-11E8-B48F-1D18A9856A87","full_name":"Sharmanska, Viktoriia"},{"last_name":"Quadrianto","first_name":"Novi","full_name":"Quadrianto, Novi"}],"date_created":"2025-07-10T13:57:52Z","month":"07","corr_author":"1","_id":"19991"},{"status":"public","article_processing_charge":"No","has_accepted_license":"1","department":[{"_id":"ChLa"}],"language":[{"iso":"eng"}],"file":[{"relation":"main_file","access_level":"open_access","creator":"system","date_created":"2018-12-12T10:12:42Z","file_id":"4961","file_name":"IST-2017-775-v1+1_main.pdf","file_size":237111,"date_updated":"2018-12-12T10:12:42Z","content_type":"application/pdf"},{"date_created":"2018-12-12T10:12:43Z","file_id":"4962","file_name":"IST-2017-775-v1+2_supplementary.pdf","creator":"system","access_level":"open_access","relation":"main_file","content_type":"application/pdf","file_size":185818,"date_updated":"2018-12-12T10:12:43Z"}],"date_updated":"2025-06-03T11:35:58Z","ddc":["006"],"publisher":"Neural Information Processing Systems Foundation","conference":{"location":"Barcelona, Spain","end_date":"2016-12-10","start_date":"2016-12-05","name":"NIPS: Neural Information Processing Systems"},"month":"12","day":"01","publist_id":"6277","ec_funded":1,"pubrep_id":"775","project":[{"_id":"2532554C-B435-11E9-9278-68D0E5697425","grant_number":"308036","call_identifier":"FP7","name":"Lifelong Learning of Visual Scene Understanding"}],"type":"conference","year":"2016","page":"3619-3627","file_date_updated":"2018-12-12T10:12:43Z","quality_controlled":"1","abstract":[{"text":"Better understanding of the potential benefits of information transfer and representation learning is an important step towards the goal of building intelligent systems that are able to persist in the world and learn over time. In this work, we consider a setting where the learner encounters a stream of tasks but is able to retain only limited information from each encountered task, such as a learned predictor. In contrast to most previous works analyzing this scenario, we do not make any distributional assumptions on the task generating process. Instead, we formulate a complexity measure that captures the diversity of the observed tasks. We provide a lifelong learning algorithm with error guarantees for every observed task (rather than on average). We show sample complexity reductions in comparison to solving every task in isolation in terms of our task complexity measure. Further, our algorithmic framework can naturally be viewed as learning a representation from encountered tasks with a neural network.","lang":"eng"}],"publication_status":"published","oa_version":"Published Version","title":"Lifelong learning with weighted majority votes","author":[{"last_name":"Pentina","first_name":"Anastasia","id":"42E87FC6-F248-11E8-B48F-1D18A9856A87","full_name":"Pentina, Anastasia"},{"full_name":"Urner, Ruth","last_name":"Urner","first_name":"Ruth"}],"date_created":"2018-12-11T11:50:08Z","scopus_import":"1","_id":"1098","citation":{"ista":"Pentina A, Urner R. 2016. Lifelong learning with weighted majority votes. NIPS: Neural Information Processing Systems, Advances in Neural Information Processing Systems, vol. 29, 3619–3627.","ieee":"A. Pentina and R. Urner, “Lifelong learning with weighted majority votes,” presented at the NIPS: Neural Information Processing Systems, Barcelona, Spain, 2016, vol. 29, pp. 3619–3627.","chicago":"Pentina, Anastasia, and Ruth Urner. “Lifelong Learning with Weighted Majority Votes,” 29:3619–27. Neural Information Processing Systems Foundation, 2016.","mla":"Pentina, Anastasia, and Ruth Urner. <i>Lifelong Learning with Weighted Majority Votes</i>. Vol. 29, Neural Information Processing Systems Foundation, 2016, pp. 3619–27.","short":"A. Pentina, R. Urner, in:, Neural Information Processing Systems Foundation, 2016, pp. 3619–3627.","ama":"Pentina A, Urner R. Lifelong learning with weighted majority votes. In: Vol 29. Neural Information Processing Systems Foundation; 2016:3619-3627.","apa":"Pentina, A., &#38; Urner, R. (2016). Lifelong learning with weighted majority votes (Vol. 29, pp. 3619–3627). Presented at the NIPS: Neural Information Processing Systems, Barcelona, Spain: Neural Information Processing Systems Foundation."},"date_published":"2016-12-01T00:00:00Z","oa":1,"user_id":"2DF688A6-F248-11E8-B48F-1D18A9856A87","acknowledgement":"This work was in parts funded by the European Research Council under the European Union’s Seventh Framework Programme (FP7/2007-2013)/ERC grant agreement no 308036.\r\n\r\n","intvolume":"        29","alternative_title":["Advances in Neural Information Processing Systems"],"volume":29},{"publist_id":"6273","day":"01","month":"09","publisher":"BMVA Press","conference":{"end_date":"2016-09-22","name":"BMVC: British Machine Vision Conference","start_date":"2016-09-19","location":"York, United Kingdom"},"year":"2016","type":"conference","project":[{"call_identifier":"FP7","name":"Lifelong Learning of Visual Scene Understanding","grant_number":"308036","_id":"2532554C-B435-11E9-9278-68D0E5697425"}],"ec_funded":1,"department":[{"_id":"ChLa"}],"publication":"Proceedings of the British Machine Vision Conference 2016","status":"public","date_updated":"2021-01-12T06:48:18Z","language":[{"iso":"eng"}],"user_id":"3E5EF7F0-F248-11E8-B48F-1D18A9856A87","citation":{"ista":"Kolesnikov A, Lampert C. 2016. Improving weakly-supervised object localization by micro-annotation. Proceedings of the British Machine Vision Conference 2016. BMVC: British Machine Vision Conference vol. 2016–September, 92.1-92.12.","ieee":"A. Kolesnikov and C. Lampert, “Improving weakly-supervised object localization by micro-annotation,” in <i>Proceedings of the British Machine Vision Conference 2016</i>, York, United Kingdom, 2016, vol. 2016–September, p. 92.1-92.12.","ama":"Kolesnikov A, Lampert C. Improving weakly-supervised object localization by micro-annotation. In: <i>Proceedings of the British Machine Vision Conference 2016</i>. Vol 2016-September. BMVA Press; 2016:92.1-92.12. doi:<a href=\"https://doi.org/10.5244/C.30.92\">10.5244/C.30.92</a>","mla":"Kolesnikov, Alexander, and Christoph Lampert. “Improving Weakly-Supervised Object Localization by Micro-Annotation.” <i>Proceedings of the British Machine Vision Conference 2016</i>, vol. 2016–September, BMVA Press, 2016, p. 92.1-92.12, doi:<a href=\"https://doi.org/10.5244/C.30.92\">10.5244/C.30.92</a>.","short":"A. Kolesnikov, C. Lampert, in:, Proceedings of the British Machine Vision Conference 2016, BMVA Press, 2016, p. 92.1-92.12.","chicago":"Kolesnikov, Alexander, and Christoph Lampert. “Improving Weakly-Supervised Object Localization by Micro-Annotation.” In <i>Proceedings of the British Machine Vision Conference 2016</i>, 2016–September:92.1-92.12. BMVA Press, 2016. <a href=\"https://doi.org/10.5244/C.30.92\">https://doi.org/10.5244/C.30.92</a>.","apa":"Kolesnikov, A., &#38; Lampert, C. (2016). Improving weakly-supervised object localization by micro-annotation. In <i>Proceedings of the British Machine Vision Conference 2016</i> (Vol. 2016–September, p. 92.1-92.12). York, United Kingdom: BMVA Press. <a href=\"https://doi.org/10.5244/C.30.92\">https://doi.org/10.5244/C.30.92</a>"},"oa":1,"date_published":"2016-09-01T00:00:00Z","scopus_import":1,"_id":"1102","date_created":"2018-12-11T11:50:09Z","doi":"10.5244/C.30.92","author":[{"first_name":"Alexander","last_name":"Kolesnikov","full_name":"Kolesnikov, Alexander","id":"2D157DB6-F248-11E8-B48F-1D18A9856A87"},{"first_name":"Christoph","orcid":"0000-0001-8622-7887","last_name":"Lampert","full_name":"Lampert, Christoph","id":"40C20FD2-F248-11E8-B48F-1D18A9856A87"}],"volume":"2016-September","acknowledgement":"This work was funded in parts by the European Research Council\r\nunder the European Union’s Seventh Framework Programme (FP7/2007-2013)/ERC grant\r\nagreement no 308036. We gratefully acknowledge the support of NVIDIA Corporation with\r\nthe donation of the GPUs used for this research.","quality_controlled":"1","main_file_link":[{"open_access":"1","url":"http://www.bmva.org/bmvc/2016/papers/paper092/paper092.pdf"}],"page":"92.1-92.12","oa_version":"Published Version","title":"Improving weakly-supervised object localization by micro-annotation","publication_status":"published","abstract":[{"text":"Weakly-supervised object localization methods tend to fail for object classes that consistently co-occur with the same background elements, e.g. trains on tracks. We propose a method to overcome these failures by adding a very small amount of model-specific additional annotation. The main idea is to cluster a deep network\\'s mid-level representations and assign object or distractor labels to each cluster. Experiments show substantially improved localization results on the challenging ILSVC2014 dataset for bounding box detection and the PASCAL VOC2012 dataset for semantic segmentation.","lang":"eng"}]},{"abstract":[{"lang":"eng","text":"Volunteer supporters play an important role in modern crisis and disaster management. In the times of mobile Internet devices, help from thousands of volunteers can be requested within a short time span, thus relieving professional helpers from minor chores or geographically spread-out tasks. However, the simultaneous availability of many volunteers also poses new problems. In particular, the volunteer efforts must be well coordinated, or otherwise situations might emerge in which too many idle volunteers at one location become more of a burden than a relief to the professionals.\r\nIn this work, we study the task of optimally assigning volunteers to selected locations, e.g. in order to perform regular measurements, to report on damage, or to distribute information or resources to the population in a crisis situation. We formulate the assignment tasks as an optimization problem and propose an effective and efficient solution procedure. Experiments on real data of the Team Österreich, consisting of over 36,000 Austrian volunteers, show the effectiveness and efficiency of our approach."}],"language":[{"iso":"eng"}],"title":"Optimal geospatial allocation of volunteers for crisis management","oa_version":"None","publication_status":"published","date_updated":"2021-01-12T06:52:39Z","status":"public","article_number":"7402041","department":[{"_id":"ChLa"}],"quality_controlled":"1","acknowledgement":"The DRIVER FP7 project has received funding from the European Unions Seventh Framework Programme for research, technological development and demonstration under grant agreement no 607798. RE-ACTA was funded within the framework of the Austrian Security Research Programme KIRAS by the Federal Ministry for Transport, Innovation and Technology.","year":"2016","type":"conference","_id":"1707","scopus_import":1,"month":"02","doi":"10.1109/ICT-DM.2015.7402041","author":[{"first_name":"Jasmin","last_name":"Pielorz","full_name":"Pielorz, Jasmin","id":"49BC895A-F248-11E8-B48F-1D18A9856A87"},{"id":"40C20FD2-F248-11E8-B48F-1D18A9856A87","full_name":"Lampert, Christoph","orcid":"0000-0001-8622-7887","last_name":"Lampert","first_name":"Christoph"}],"date_created":"2018-12-11T11:53:35Z","conference":{"location":"Rennes, France","start_date":"2015-11-30","name":"ICT-DM: Information and Communication Technologies for Disaster Management","end_date":"2015-12-02"},"publisher":"IEEE","publist_id":"5429","day":"11","user_id":"3E5EF7F0-F248-11E8-B48F-1D18A9856A87","date_published":"2016-02-11T00:00:00Z","citation":{"ieee":"J. Pielorz and C. Lampert, “Optimal geospatial allocation of volunteers for crisis management,” presented at the ICT-DM: Information and Communication Technologies for Disaster Management, Rennes, France, 2016.","ista":"Pielorz J, Lampert C. 2016. Optimal geospatial allocation of volunteers for crisis management. ICT-DM: Information and Communication Technologies for Disaster Management, 7402041.","apa":"Pielorz, J., &#38; Lampert, C. (2016). Optimal geospatial allocation of volunteers for crisis management. Presented at the ICT-DM: Information and Communication Technologies for Disaster Management, Rennes, France: IEEE. <a href=\"https://doi.org/10.1109/ICT-DM.2015.7402041\">https://doi.org/10.1109/ICT-DM.2015.7402041</a>","short":"J. Pielorz, C. Lampert, in:, IEEE, 2016.","mla":"Pielorz, Jasmin, and Christoph Lampert. <i>Optimal Geospatial Allocation of Volunteers for Crisis Management</i>. 7402041, IEEE, 2016, doi:<a href=\"https://doi.org/10.1109/ICT-DM.2015.7402041\">10.1109/ICT-DM.2015.7402041</a>.","chicago":"Pielorz, Jasmin, and Christoph Lampert. “Optimal Geospatial Allocation of Volunteers for Crisis Management.” IEEE, 2016. <a href=\"https://doi.org/10.1109/ICT-DM.2015.7402041\">https://doi.org/10.1109/ICT-DM.2015.7402041</a>.","ama":"Pielorz J, Lampert C. Optimal geospatial allocation of volunteers for crisis management. In: IEEE; 2016. doi:<a href=\"https://doi.org/10.1109/ICT-DM.2015.7402041\">10.1109/ICT-DM.2015.7402041</a>"}},{"language":[{"iso":"eng"}],"ddc":["610"],"file":[{"relation":"main_file","access_level":"open_access","creator":"cziletti","file_id":"8096","date_created":"2020-07-06T12:59:09Z","file_name":"2016_ProcALIFE_Martius.pdf","checksum":"cff63e7a4b8ac466ba51a9c84153a940","content_type":"application/pdf","date_updated":"2020-07-14T12:48:09Z","file_size":678670}],"date_updated":"2025-07-10T11:55:05Z","status":"public","has_accepted_license":"1","department":[{"_id":"ChLa"},{"_id":"GaTk"}],"publication":"15th International Conference on the Synthesis and Simulation of Living Systems","article_processing_charge":"No","tmp":{"name":"Creative Commons Attribution 4.0 International Public License (CC-BY 4.0)","short":"CC BY (4.0)","legal_code_url":"https://creativecommons.org/licenses/by/4.0/legalcode","image":"/images/cc_by.png"},"ec_funded":1,"year":"2016","project":[{"_id":"25681D80-B435-11E9-9278-68D0E5697425","call_identifier":"FP7","name":"International IST Postdoc Fellowship Programme","grant_number":"291734"}],"type":"conference","month":"09","corr_author":"1","publisher":"MIT Press","conference":{"location":"Cancun, Mexico","start_date":"2016-07-04","name":"ALIFE 2016: Conference on the Synthesis and Simulation of Living Systems","end_date":"2016-07-08"},"day":"01","abstract":[{"text":"With the accelerated development of robot technologies, optimal control becomes one of the central themes of research. In traditional approaches, the controller, by its internal functionality, finds appropriate actions on the basis of the history of sensor values, guided by the goals, intentions, objectives, learning schemes, and so forth. The idea is that the controller controls the world---the body plus its environment---as reliably as possible. This paper focuses on new lines of self-organization for developmental robotics. We apply the recently developed differential extrinsic synaptic plasticity to a muscle-tendon driven arm-shoulder system from the Myorobotics toolkit. In the experiments, we observe a vast variety of self-organized behavior patterns: when left alone, the arm realizes pseudo-random sequences of different poses. By applying physical forces, the system can be entrained into definite motion patterns like wiping a table. Most interestingly, after attaching an object, the controller gets in a functional resonance with the object's internal dynamics, starting to shake spontaneously bottles half-filled with water or sensitively driving an attached pendulum into a circular mode. When attached to the crank of a wheel the neural system independently discovers how to rotate it. In this way, the robot discovers affordances of objects its body is interacting with.","lang":"eng"}],"title":"Self-organized control of an tendon driven arm by differential extrinsic plasticity","oa_version":"Published Version","publication_status":"published","page":"142-143","file_date_updated":"2020-07-14T12:48:09Z","quality_controlled":"1","intvolume":"        28","publication_identifier":{"isbn":["9780262339360"]},"volume":28,"scopus_import":"1","_id":"8094","doi":"10.7551/978-0-262-33936-0-ch029","author":[{"last_name":"Martius","first_name":"Georg S","id":"3A276B68-F248-11E8-B48F-1D18A9856A87","full_name":"Martius, Georg S"},{"full_name":"Hostettler, Rafael","last_name":"Hostettler","first_name":"Rafael"},{"full_name":"Knoll, Alois","last_name":"Knoll","first_name":"Alois"},{"full_name":"Der, Ralf","first_name":"Ralf","last_name":"Der"}],"date_created":"2020-07-05T22:00:47Z","user_id":"2DF688A6-F248-11E8-B48F-1D18A9856A87","citation":{"ista":"Martius GS, Hostettler R, Knoll A, Der R. 2016. Self-organized control of an tendon driven arm by differential extrinsic plasticity. 15th International Conference on the Synthesis and Simulation of Living Systems. ALIFE 2016: Conference on the Synthesis and Simulation of Living Systems vol. 28, 142–143.","ieee":"G. S. Martius, R. Hostettler, A. Knoll, and R. Der, “Self-organized control of an tendon driven arm by differential extrinsic plasticity,” in <i>15th International Conference on the Synthesis and Simulation of Living Systems</i>, Cancun, Mexico, 2016, vol. 28, pp. 142–143.","mla":"Martius, Georg S., et al. “Self-Organized Control of an Tendon Driven Arm by Differential Extrinsic Plasticity.” <i>15th International Conference on the Synthesis and Simulation of Living Systems</i>, vol. 28, MIT Press, 2016, pp. 142–43, doi:<a href=\"https://doi.org/10.7551/978-0-262-33936-0-ch029\">10.7551/978-0-262-33936-0-ch029</a>.","short":"G.S. Martius, R. Hostettler, A. Knoll, R. Der, in:, 15th International Conference on the Synthesis and Simulation of Living Systems, MIT Press, 2016, pp. 142–143.","chicago":"Martius, Georg S, Rafael Hostettler, Alois Knoll, and Ralf Der. “Self-Organized Control of an Tendon Driven Arm by Differential Extrinsic Plasticity.” In <i>15th International Conference on the Synthesis and Simulation of Living Systems</i>, 28:142–43. MIT Press, 2016. <a href=\"https://doi.org/10.7551/978-0-262-33936-0-ch029\">https://doi.org/10.7551/978-0-262-33936-0-ch029</a>.","ama":"Martius GS, Hostettler R, Knoll A, Der R. Self-organized control of an tendon driven arm by differential extrinsic plasticity. In: <i>15th International Conference on the Synthesis and Simulation of Living Systems</i>. Vol 28. MIT Press; 2016:142-143. doi:<a href=\"https://doi.org/10.7551/978-0-262-33936-0-ch029\">10.7551/978-0-262-33936-0-ch029</a>","apa":"Martius, G. S., Hostettler, R., Knoll, A., &#38; Der, R. (2016). Self-organized control of an tendon driven arm by differential extrinsic plasticity. In <i>15th International Conference on the Synthesis and Simulation of Living Systems</i> (Vol. 28, pp. 142–143). Cancun, Mexico: MIT Press. <a href=\"https://doi.org/10.7551/978-0-262-33936-0-ch029\">https://doi.org/10.7551/978-0-262-33936-0-ch029</a>"},"date_published":"2016-09-01T00:00:00Z","oa":1},{"page":"127","file_date_updated":"2018-12-12T10:14:07Z","abstract":[{"text":"Traditionally machine learning has been focusing on the problem of solving a single\r\ntask in isolation. While being quite well understood, this approach disregards an\r\nimportant aspect of human learning: when facing a new problem, humans are able to\r\nexploit knowledge acquired from previously learned tasks. Intuitively, access to several\r\nproblems simultaneously or sequentially could also be advantageous for a machine\r\nlearning system, especially if these tasks are closely related. Indeed, results of many\r\nempirical studies have provided justification for this intuition. However, theoretical\r\njustifications of this idea are rather limited.\r\nThe focus of this thesis is to expand the understanding of potential benefits of information\r\ntransfer between several related learning problems. We provide theoretical\r\nanalysis for three scenarios of multi-task learning - multiple kernel learning, sequential\r\nlearning and active task selection. We also provide a PAC-Bayesian perspective on\r\nlifelong learning and investigate how the task generation process influences the generalization\r\nguarantees in this scenario. In addition, we show how some of the obtained\r\ntheoretical results can be used to derive principled multi-task and lifelong learning\r\nalgorithms and illustrate their performance on various synthetic and real-world datasets.","lang":"eng"}],"title":"Theoretical foundations of multi-task lifelong learning","oa_version":"Published Version","publication_status":"published","OA_place":"publisher","_id":"1126","doi":"10.15479/AT:ISTA:TH_776","author":[{"first_name":"Anastasia","last_name":"Pentina","full_name":"Pentina, Anastasia","id":"42E87FC6-F248-11E8-B48F-1D18A9856A87"}],"date_created":"2018-12-11T11:50:17Z","user_id":"ba8df636-2132-11f1-aed0-ed93e2281fdd","citation":{"ieee":"A. Pentina, “Theoretical foundations of multi-task lifelong learning,” Institute of Science and Technology Austria, 2016.","ista":"Pentina A. 2016. Theoretical foundations of multi-task lifelong learning. Institute of Science and Technology Austria.","apa":"Pentina, A. (2016). <i>Theoretical foundations of multi-task lifelong learning</i>. Institute of Science and Technology Austria. <a href=\"https://doi.org/10.15479/AT:ISTA:TH_776\">https://doi.org/10.15479/AT:ISTA:TH_776</a>","ama":"Pentina A. Theoretical foundations of multi-task lifelong learning. 2016. doi:<a href=\"https://doi.org/10.15479/AT:ISTA:TH_776\">10.15479/AT:ISTA:TH_776</a>","mla":"Pentina, Anastasia. <i>Theoretical Foundations of Multi-Task Lifelong Learning</i>. Institute of Science and Technology Austria, 2016, doi:<a href=\"https://doi.org/10.15479/AT:ISTA:TH_776\">10.15479/AT:ISTA:TH_776</a>.","short":"A. Pentina, Theoretical Foundations of Multi-Task Lifelong Learning, Institute of Science and Technology Austria, 2016.","chicago":"Pentina, Anastasia. “Theoretical Foundations of Multi-Task Lifelong Learning.” Institute of Science and Technology Austria, 2016. <a href=\"https://doi.org/10.15479/AT:ISTA:TH_776\">https://doi.org/10.15479/AT:ISTA:TH_776</a>."},"supervisor":[{"first_name":"Christoph","orcid":"0000-0001-8622-7887","last_name":"Lampert","full_name":"Lampert, Christoph","id":"40C20FD2-F248-11E8-B48F-1D18A9856A87"}],"oa":1,"date_published":"2016-11-01T00:00:00Z","acknowledgement":"First and foremost I would like to express my gratitude to my supervisor, Christoph\r\nLampert. Thank you for your patience in teaching me all aspects of doing research\r\n(including English grammar), for your trust in my capabilities and endless support. Thank\r\nyou for granting me freedom in my research and, at the same time, having time and\r\nhelping me cope with the consequences whenever I needed it. Thank you for creating\r\nan excellent atmosphere in the group, it was a great pleasure and honor to be a part of\r\nit. There could not have been a better and more inspiring adviser and mentor.\r\nI thank Shai Ben-David for welcoming me into his group at the University of Waterloo,\r\nfor inspiring discussions and support. It was a great pleasure to work together. I am\r\nalso thankful to Ruth Urner for hosting me at the Max-Planck Institute Tübingen, for the\r\nfruitful collaboration and for taking care of me during that not-so-sunny month of May.\r\nI thank Jan Maas for kindly joining my thesis committee despite the short notice and\r\nproviding me with insightful comments.\r\nI would like to thank my colleagues for their support, entertaining conversations and\r\nendless table soccer games we shared together: Georg, Jan, Amelie and Emilie, Michal\r\nand Alex, Alex K. and Alex Z., Thomas, Sameh, Vlad, Mayu, Nathaniel, Silvester, Neel,\r\nCsaba, Vladimir, Morten. Thank you, Mabel and Ram, for the wonderful time we spent\r\ntogether. I am thankful to Shrinu and Samira for taking care of me during my stay at the\r\nUniversity of Waterloo. Special thanks to Viktoriia for her never-ending optimism and for\r\nbeing so inspiring and supportive, especially at the beginning of my PhD journey.\r\nThanks to IST administration, in particular, Vlad and Elisabeth for shielding me from\r\nmost of the bureaucratic paperwork.\r\n\r\nThis dissertation would not have been possible without funding from the European\r\nResearch Council under the European Union's Seventh Framework Programme\r\n(FP7/2007-2013)/ERC grant agreement no 308036.","alternative_title":["ISTA Thesis"],"publication_identifier":{"issn":["2663-337X"]},"status":"public","has_accepted_license":"1","department":[{"_id":"ChLa"}],"article_processing_charge":"No","language":[{"iso":"eng"}],"ddc":["006"],"date_updated":"2026-04-09T10:49:34Z","file":[{"file_size":2140062,"date_updated":"2018-12-12T10:14:07Z","content_type":"application/pdf","access_level":"open_access","creator":"system","date_created":"2018-12-12T10:14:07Z","file_name":"IST-2017-776-v1+1_Pentina_Thesis_2016.pdf","file_id":"5056","relation":"main_file"}],"month":"11","corr_author":"1","publisher":"Institute of Science and Technology Austria","publist_id":"6234","day":"01","degree_awarded":"PhD","ec_funded":1,"year":"2016","pubrep_id":"776","project":[{"_id":"2532554C-B435-11E9-9278-68D0E5697425","grant_number":"308036","call_identifier":"FP7","name":"Lifelong Learning of Visual Scene Understanding"}],"type":"dissertation"},{"month":"01","publisher":"Neural Information Processing Systems Foundation","conference":{"start_date":"2015-12-07","name":"NIPS: Neural Information Processing Systems","end_date":"2015-12-12","location":"Montreal, Canada"},"publist_id":"5781","day":"01","ec_funded":1,"year":"2015","project":[{"_id":"2532554C-B435-11E9-9278-68D0E5697425","grant_number":"308036","name":"Lifelong Learning of Visual Scene Understanding","call_identifier":"FP7"}],"type":"conference","status":"public","department":[{"_id":"ChLa"}],"article_processing_charge":"No","language":[{"iso":"eng"}],"date_updated":"2025-06-03T11:41:45Z","scopus_import":"1","_id":"1425","date_created":"2018-12-11T11:51:57Z","author":[{"full_name":"Pentina, Anastasia","id":"42E87FC6-F248-11E8-B48F-1D18A9856A87","first_name":"Anastasia","last_name":"Pentina"},{"full_name":"Lampert, Christoph","id":"40C20FD2-F248-11E8-B48F-1D18A9856A87","first_name":"Christoph","orcid":"0000-0001-8622-7887","last_name":"Lampert"}],"user_id":"2DF688A6-F248-11E8-B48F-1D18A9856A87","citation":{"ista":"Pentina A, Lampert C. 2015. Lifelong learning with non-i.i.d. tasks. NIPS: Neural Information Processing Systems, Advances in Neural Information Processing Systems, vol. 2015, 1540–1548.","ieee":"A. Pentina and C. Lampert, “Lifelong learning with non-i.i.d. tasks,” presented at the NIPS: Neural Information Processing Systems, Montreal, Canada, 2015, vol. 2015, pp. 1540–1548.","chicago":"Pentina, Anastasia, and Christoph Lampert. “Lifelong Learning with Non-i.i.d. Tasks,” 2015:1540–48. Neural Information Processing Systems Foundation, 2015.","mla":"Pentina, Anastasia, and Christoph Lampert. <i>Lifelong Learning with Non-i.i.d. Tasks</i>. Vol. 2015, Neural Information Processing Systems Foundation, 2015, pp. 1540–48.","short":"A. Pentina, C. Lampert, in:, Neural Information Processing Systems Foundation, 2015, pp. 1540–1548.","ama":"Pentina A, Lampert C. Lifelong learning with non-i.i.d. tasks. In: Vol 2015. Neural Information Processing Systems Foundation; 2015:1540-1548.","apa":"Pentina, A., &#38; Lampert, C. (2015). Lifelong learning with non-i.i.d. tasks (Vol. 2015, pp. 1540–1548). Presented at the NIPS: Neural Information Processing Systems, Montreal, Canada: Neural Information Processing Systems Foundation."},"oa":1,"date_published":"2015-01-01T00:00:00Z","intvolume":"      2015","alternative_title":["Advances in Neural Information Processing Systems"],"volume":2015,"main_file_link":[{"open_access":"1","url":"http://papers.nips.cc/paper/6007-lifelong-learning-with-non-iid-tasks"}],"page":"1540 - 1548","quality_controlled":"1","abstract":[{"text":"In this work we aim at extending the theoretical foundations of lifelong learning. Previous work analyzing this scenario is based on the assumption that learning tasks are sampled i.i.d. from a task environment or limited to strongly constrained data distributions. Instead, we study two scenarios when lifelong learning is possible, even though the observed tasks do not form an i.i.d. sample: first, when they are sampled from the same environment, but possibly with dependencies, and second, when the task environment is allowed to change over time in a consistent way. In the first case we prove a PAC-Bayesian theorem that can be seen as a direct generalization of the analogous previous result for the i.i.d. case. For the second scenario we propose to learn an inductive bias in form of a transfer procedure. We present a generalization bound and show on a toy example how it can be used to identify a beneficial transfer algorithm.","lang":"eng"}],"title":"Lifelong learning with non-i.i.d. tasks","oa_version":"None","publication_status":"published"},{"corr_author":"1","month":"06","conference":{"location":"Boston, MA, United States","end_date":"2015-06-12","start_date":"2015-06-07","name":"CVPR: Computer Vision and Pattern Recognition"},"publisher":"IEEE","publist_id":"5243","day":"01","year":"2015","type":"conference","status":"public","external_id":{"arxiv":["1412.1353"]},"department":[{"_id":"ChLa"}],"article_processing_charge":"No","language":[{"iso":"eng"}],"date_updated":"2025-06-11T07:19:52Z","_id":"1857","scopus_import":"1","date_created":"2018-12-11T11:54:23Z","author":[{"first_name":"Anastasia","last_name":"Pentina","full_name":"Pentina, Anastasia","id":"42E87FC6-F248-11E8-B48F-1D18A9856A87"},{"orcid":"0000-0003-0192-9308","last_name":"Sharmanska","first_name":"Viktoriia","id":"2EA6D09E-F248-11E8-B48F-1D18A9856A87","full_name":"Sharmanska, Viktoriia"},{"first_name":"Christoph","last_name":"Lampert","orcid":"0000-0001-8622-7887","full_name":"Lampert, Christoph","id":"40C20FD2-F248-11E8-B48F-1D18A9856A87"}],"doi":"10.1109/CVPR.2015.7299188","user_id":"2DF688A6-F248-11E8-B48F-1D18A9856A87","date_published":"2015-06-01T00:00:00Z","oa":1,"arxiv":1,"citation":{"ama":"Pentina A, Sharmanska V, Lampert C. Curriculum learning of multiple tasks. In: IEEE; 2015:5492-5500. doi:<a href=\"https://doi.org/10.1109/CVPR.2015.7299188\">10.1109/CVPR.2015.7299188</a>","mla":"Pentina, Anastasia, et al. <i>Curriculum Learning of Multiple Tasks</i>. IEEE, 2015, pp. 5492–500, doi:<a href=\"https://doi.org/10.1109/CVPR.2015.7299188\">10.1109/CVPR.2015.7299188</a>.","short":"A. Pentina, V. Sharmanska, C. Lampert, in:, IEEE, 2015, pp. 5492–5500.","chicago":"Pentina, Anastasia, Viktoriia Sharmanska, and Christoph Lampert. “Curriculum Learning of Multiple Tasks,” 5492–5500. IEEE, 2015. <a href=\"https://doi.org/10.1109/CVPR.2015.7299188\">https://doi.org/10.1109/CVPR.2015.7299188</a>.","apa":"Pentina, A., Sharmanska, V., &#38; Lampert, C. (2015). Curriculum learning of multiple tasks (pp. 5492–5500). Presented at the CVPR: Computer Vision and Pattern Recognition, Boston, MA, United States: IEEE. <a href=\"https://doi.org/10.1109/CVPR.2015.7299188\">https://doi.org/10.1109/CVPR.2015.7299188</a>","ista":"Pentina A, Sharmanska V, Lampert C. 2015. Curriculum learning of multiple tasks. CVPR: Computer Vision and Pattern Recognition, 5492–5500.","ieee":"A. Pentina, V. Sharmanska, and C. Lampert, “Curriculum learning of multiple tasks,” presented at the CVPR: Computer Vision and Pattern Recognition, Boston, MA, United States, 2015, pp. 5492–5500."},"main_file_link":[{"open_access":"1","url":"http://arxiv.org/abs/1412.1353"}],"page":"5492 - 5500","quality_controlled":"1","abstract":[{"text":"Sharing information between multiple tasks enables algorithms to achieve good generalization performance even from small amounts of training data. However, in a realistic scenario of multi-task learning not all tasks are equally related to each other, hence it could be advantageous to transfer information only between the most related tasks. In this work we propose an approach that processes multiple tasks in a sequence with sharing between subsequent tasks instead of solving all tasks jointly. Subsequently, we address the question of curriculum learning of tasks, i.e. finding the best order of tasks to be learned. Our approach is based on a generalization bound criterion for choosing the task order that optimizes the average expected classification performance over all tasks. Our experimental results show that learning multiple related tasks sequentially can be more effective than learning them jointly, the order in which tasks are being solved affects the overall performance, and that our model is able to automatically discover the favourable order of tasks. ","lang":"eng"}],"oa_version":"Preprint","title":"Curriculum learning of multiple tasks","publication_status":"published"}]