@phdthesis{19456,
  abstract     = {Making decisions requires flexibly adapting to changing environments, a process that
depends on accurately interpreting current contingencies and integrating them with
past experience. Two brain regions are particularly critical for this process, the medial
prefrontal cortex (mPFC) and the hippocampus. Using contextual information from the
hippocampus, the mPFC selects relevant cognitive frameworks and suppresses
irrelevant ones to guide appropriate actions. Several studies have shown that some
mPFC pyramidal neurons become spatially tuned when spatial information is required
to guide goal-directed behavior. However, the role of prefrontal spatial representations
in learning and decision making is not well understood. This work aims to characterize
the role of mPFC spatial tuning in supporting a contextual association task. Rats were
trained to learn two cue–location associations on a radial arm maze over multiple days,
while we simultaneously recorded from dorsal CA1 of the hippocampus and the
prelimbic area of the mPFC. We describe a subset of spatially tuned hippocampal and
prefrontal pyramidal neurons that “flicker” between multiple spatial representations on
different trials, suggesting dynamic, context-dependent coding. This flickering may
provide a substrate for how the network reorganizes in response to task demands,
likely by enabling the flexible evaluation of competing representations. },
  author       = {Cumpelik, Andrea D},
  isbn         = {978-3-99078-056-5},
  issn         = {2663-337X},
  keywords     = {neuroscience, decision making, learning, cognitive flexibility, medial prefrontal cortex, hippocampus, electrophysiology},
  pages        = {96},
  publisher    = {Institute of Science and Technology Austria},
  title        = {{The role of prefrontal spatial coding in supporting a contextual association task}},
  doi          = {10.15479/AT-ISTA-19456},
  year         = {2025},
}

@inproceedings{12976,
  abstract     = {3D printing based on continuous deposition of materials, such as filament-based 3D printing, has seen widespread adoption thanks to its versatility in working with a wide range of materials. An important shortcoming of this type of technology is its limited multi-material capabilities. While there are simple hardware designs that enable multi-material printing in principle, the required software is heavily underdeveloped. A typical hardware design fuses together individual materials fed into a single chamber from multiple inlets before they are deposited. This design, however, introduces a time delay between the intended material mixture and its actual deposition. In this work, inspired by diverse path planning research in robotics, we show that this mechanical challenge can be addressed via improved printer control. We propose to formulate the search for optimal multi-material printing policies in a reinforcement
learning setup. We put forward a simple numerical deposition model that takes into account the non-linear material mixing and delayed material deposition. To validate our system we focus on color fabrication, a problem known for its strict requirements for varying material mixtures at a high spatial frequency. We demonstrate that our learned control policy outperforms state-of-the-art hand-crafted algorithms.},
  author       = {Liao, Kang and Tricard, Thibault and Piovarci, Michael and Seidel, Hans-Peter and Babaei, Vahid},
  booktitle    = {2023 IEEE International Conference on Robotics and Automation},
  issn         = {1050-4729},
  keywords     = {reinforcement learning, deposition, control, color, multi-filament},
  location     = {London, United Kingdom},
  pages        = {12345--12352},
  publisher    = {IEEE},
  title        = {{Learning deposition policies for fused multi-material 3D printing}},
  doi          = {10.1109/ICRA48891.2023.10160465},
  volume       = {2023},
  year         = {2023},
}

@phdthesis{10799,
  abstract     = {Because of the increasing popularity of machine learning methods, it is becoming important to understand the impact of learned components on automated decision-making systems and to guarantee that their consequences are beneficial to society. In other words, it is necessary to ensure that machine learning is sufficiently trustworthy to be used in real-world applications. This thesis studies two properties of machine learning models that are highly desirable for the
sake of reliability: robustness and fairness. In the first part of the thesis we study the robustness of learning algorithms to training data corruption. Previous work has shown that machine learning models are vulnerable to a range
of training set issues, varying from label noise through systematic biases to worst-case data manipulations. This is an especially relevant problem from a present perspective, since modern machine learning methods are particularly data hungry and therefore practitioners often have to rely on data collected from various external sources, e.g. from the Internet, from app users or via crowdsourcing. Naturally, such sources vary greatly in the quality and reliability of the
data they provide. With these considerations in mind, we study the problem of designing machine learning algorithms that are robust to corruptions in data coming from multiple sources. We show that, in contrast to the case of a single dataset with outliers, successful learning within this model is possible both theoretically and practically, even under worst-case data corruptions. The second part of this thesis deals with fairness-aware machine learning. There are multiple areas where machine learning models have shown promising results, but where careful considerations are required, in order to avoid discrimanative decisions taken by such learned components. Ensuring fairness can be particularly challenging, because real-world training datasets are expected to contain various forms of historical bias that may affect the learning process. In this thesis we show that data corruption can indeed render the problem of achieving fairness impossible, by tightly characterizing the theoretical limits of fair learning under worst-case data manipulations. However, assuming access to clean data, we also show how fairness-aware learning can be made practical in contexts beyond binary classification, in particular in the challenging learning to rank setting.},
  author       = {Konstantinov, Nikola H},
  isbn         = {978-3-99078-015-2},
  issn         = {2663-337X},
  keywords     = {robustness, fairness, machine learning, PAC learning, adversarial learning},
  pages        = {176},
  publisher    = {Institute of Science and Technology Austria},
  title        = {{Robustness and fairness in machine learning}},
  doi          = {10.15479/at:ista:10799},
  year         = {2022},
}

@article{10802,
  abstract     = {Addressing fairness concerns about machine learning models is a crucial step towards their long-term adoption in real-world automated systems. While many approaches have been developed for training fair models from data, little is known about the robustness of these methods to data corruption. In this work we consider fairness-aware learning under worst-case data manipulations. We show that an adversary can in some situations force any learner to return an overly biased classifier, regardless of the sample size and with or without degrading
accuracy, and that the strength of the excess bias increases for learning problems with underrepresented protected groups in the data. We also prove that our hardness results are tight up to constant factors. To this end, we study two natural learning algorithms that optimize for both accuracy and fairness and show that these algorithms enjoy guarantees that are order-optimal in terms of the corruption ratio and the protected groups frequencies in the large data
limit.},
  author       = {Konstantinov, Nikola H and Lampert, Christoph},
  issn         = {1533-7928},
  journal      = {Journal of Machine Learning Research},
  keywords     = {Fairness, robustness, data poisoning, trustworthy machine learning, PAC learning},
  pages        = {1--60},
  publisher    = {ML Research Press},
  title        = {{Fairness-aware PAC learning from corrupted data}},
  volume       = {23},
  year         = {2022},
}

@phdthesis{11362,
  abstract     = {Deep learning has enabled breakthroughs in challenging computing problems and has emerged as the standard problem-solving tool for computer vision and natural language processing tasks.
One exception to this trend is safety-critical tasks where robustness and resilience requirements contradict the black-box nature of neural networks. 
To deploy deep learning methods for these tasks, it is vital to provide guarantees on neural network agents' safety and robustness criteria. 
This can be achieved by developing formal verification methods to verify the safety and robustness properties of neural networks.

Our goal is to design, develop and assess safety verification methods for neural networks to improve their reliability and trustworthiness in real-world applications.
This thesis establishes techniques for the verification of compressed and adversarially trained models as well as the design of novel neural networks for verifiably safe decision-making.

First, we establish the problem of verifying quantized neural networks. Quantization is a technique that trades numerical precision for the computational efficiency of running a neural network and is widely adopted in industry.
We show that neglecting the reduced precision when verifying a neural network can lead to wrong conclusions about the robustness and safety of the network, highlighting that novel techniques for quantized network verification are necessary. We introduce several bit-exact verification methods explicitly designed for quantized neural networks and experimentally confirm on realistic networks that the network's robustness and other formal properties are affected by the quantization.

Furthermore, we perform a case study providing evidence that adversarial training, a standard technique for making neural networks more robust, has detrimental effects on the network's performance. This robustness-accuracy tradeoff has been studied before regarding the accuracy obtained on classification datasets where each data point is independent of all other data points. On the other hand, we investigate the tradeoff empirically in robot learning settings where a both, a high accuracy and a high robustness, are desirable.
Our results suggest that the negative side-effects of adversarial training outweigh its robustness benefits in practice.

Finally, we consider the problem of verifying safety when running a Bayesian neural network policy in a feedback loop with systems over the infinite time horizon. Bayesian neural networks are probabilistic models for learning uncertainties in the data and are therefore often used on robotic and healthcare applications where data is inherently stochastic.
We introduce a method for recalibrating Bayesian neural networks so that they yield probability distributions over safe decisions only.
Our method learns a safety certificate that guarantees safety over the infinite time horizon to determine which decisions are safe in every possible state of the system.
We demonstrate the effectiveness of our approach on a series of reinforcement learning benchmarks.},
  author       = {Lechner, Mathias},
  isbn         = {978-3-99078-017-6},
  keywords     = {neural networks, verification, machine learning},
  pages        = {124},
  publisher    = {Institute of Science and Technology Austria},
  title        = {{Learning verifiable representations}},
  doi          = {10.15479/at:ista:11362},
  year         = {2022},
}

@inbook{9756,
  abstract     = {High-resolution visualization and quantification of membrane proteins contribute to the understanding of their functions and the roles they play in physiological and pathological conditions. Sodium dodecyl sulfate-digested freeze-fracture replica labeling (SDS-FRL) is a powerful electron microscopy method to study quantitatively the two-dimensional distribution of transmembrane proteins and their tightly associated proteins. During treatment with SDS, intracellular organelles and proteins not anchored to the replica are dissolved, whereas integral membrane proteins captured and stabilized by carbon/platinum deposition remain on the replica. Their intra- and extracellular domains become exposed on the surface of the replica, facilitating the accessibility of antibodies and, therefore, providing higher labeling efficiency than those obtained with other immunoelectron microscopy techniques. In this chapter, we describe the protocols of SDS-FRL adapted for mammalian brain samples, and optimization of the SDS treatment to increase the labeling efficiency for quantification of Cav2.1, the alpha subunit of P/Q-type voltage-dependent calcium channels utilizing deep learning algorithms.},
  author       = {Kaufmann, Walter and Kleindienst, David and Harada, Harumi and Shigemoto, Ryuichi},
  booktitle    = { Receptor and Ion Channel Detection in the Brain},
  isbn         = {9781071615218},
  keywords     = {Freeze-fracture replica: Deep learning, Immunogold labeling, Integral membrane protein, Electron microscopy},
  pages        = {267--283},
  publisher    = {Humana},
  title        = {{High-Resolution localization and quantitation of membrane proteins by SDS-digested freeze-fracture replica labeling (SDS-FRL)}},
  doi          = {10.1007/978-1-0716-1522-5_19},
  volume       = {169},
  year         = {2021},
}

@unpublished{11627,
  abstract     = {For a solar-like star, the surface rotation evolves with time, allowing in principle to estimate the age of a star from its surface rotation period. Here we are interested in measuring surface rotation periods of solar-like stars observed by the NASA mission Kepler. Different methods have been developed to track rotation signals in Kepler photometric light curves: time-frequency analysis based on wavelet techniques, autocorrelation and composite spectrum. We use the learning abilities of random forest classifiers to take decisions during two crucial steps of the analysis. First, given some input parameters, we discriminate the considered Kepler targets between rotating MS stars, non-rotating MS stars, red giants, binaries and pulsators. We then use a second classifier only on the MS rotating targets to decide the best data analysis treatment.},
  author       = {Breton, S. N. and Bugnet, Lisa Annabelle and Santos, A. R. G. and Saux, A. Le and Mathur, S. and Palle, P. L. and Garcia, R. A.},
  booktitle    = {arXiv},
  keywords     = {asteroseismology, rotation, solar-like stars, kepler, machine learning, random forest},
  title        = {{Determining surface rotation periods of solar-like stars observed by the Kepler mission using machine learning techniques}},
  doi          = {10.48550/arXiv.1906.09609},
  year         = {2019},
}

@unpublished{11630,
  abstract     = {The second mission of NASA’s Kepler satellite, K2, has collected hundreds of thousands of lightcurves for stars close to the ecliptic plane. This new sample could increase the number of known pulsating stars and then improve our understanding of those stars. For the moment only a few stars have been properly classified and published. In this work, we present a method to automaticly classify K2 pulsating stars using a Machine Learning technique called Random Forest. The objective is to sort out the stars in four classes: red giant (RG), main-sequence Solar-like stars (SL), classical pulsators (PULS) and Other. To do this we use the effective temperatures and the luminosities of the stars as well as the FliPer features, that measures the amount of power contained in the power spectral density. The classifier now retrieves the right classification for more than 80% of the stars.},
  author       = {Saux, A. Le and Bugnet, Lisa Annabelle and Mathur, S. and Breton, S. N. and Garcia, R. A.},
  booktitle    = {arXiv},
  keywords     = {asteroseismology - methods, data analysis - thecniques, machine learning - stars, oscillations},
  title        = {{Automatic classification of K2 pulsating stars using machine learning techniques}},
  doi          = {10.48550/arXiv.1906.09611},
  year         = {2019},
}