{"has_accepted_license":"1","publication_status":"published","date_published":"2022-12-01T00:00:00Z","file_date_updated":"2023-07-18T06:32:38Z","oa":1,"year":"2022","_id":"13239","ddc":["000"],"abstract":[{"lang":"eng","text":"Brains are thought to engage in predictive learning - learning to predict upcoming stimuli - to construct an internal model of their environment. This is especially notable for spatial navigation, as first described by Tolman’s latent learning tasks. However, predictive learning has also been observed in sensory cortex, in settings unrelated to spatial navigation. Apart from normative frameworks such as active inference or efficient coding, what could be the utility of learning to predict the patterns of occurrence of correlated stimuli? Here we show that prediction, and thereby the construction of an internal model of sequential stimuli, can bootstrap the learning process of a working memory task in a recurrent neural network. We implemented predictive learning alongside working memory match-tasks, and networks emerged to solve the prediction task first by encoding information across time to predict upcoming stimuli, and then eavesdropped on this solution to solve the matching task. Eavesdropping was most beneficial when neural resources were limited. Hence, predictive learning acts as a general neural mechanism to learn to store sensory information that can later be essential for working memory tasks."}],"month":"12","language":[{"iso":"eng"}],"scopus_import":"1","citation":{"short":"T.L. Van Der Plas, T.P. Vogels, S.G. Manohar, in:, Proceedings of Machine Learning Research, ML Research Press, 2022, pp. 518–531.","chicago":"Van Der Plas, Thijs L., Tim P Vogels, and Sanjay G. Manohar. “Predictive Learning Enables Neural Networks to Learn Complex Working Memory Tasks.” In <i>Proceedings of Machine Learning Research</i>, 199:518–31. ML Research Press, 2022.","ieee":"T. L. Van Der Plas, T. P. Vogels, and S. G. Manohar, “Predictive learning enables neural networks to learn complex working memory tasks,” in <i>Proceedings of Machine Learning Research</i>, 2022, vol. 199, pp. 518–531.","ista":"Van Der Plas TL, Vogels TP, Manohar SG. 2022. Predictive learning enables neural networks to learn complex working memory tasks. Proceedings of Machine Learning Research. vol. 199, 518–531.","ama":"Van Der Plas TL, Vogels TP, Manohar SG. Predictive learning enables neural networks to learn complex working memory tasks. In: <i>Proceedings of Machine Learning Research</i>. Vol 199. ML Research Press; 2022:518-531.","apa":"Van Der Plas, T. L., Vogels, T. P., &#38; Manohar, S. G. (2022). Predictive learning enables neural networks to learn complex working memory tasks. In <i>Proceedings of Machine Learning Research</i> (Vol. 199, pp. 518–531). ML Research Press.","mla":"Van Der Plas, Thijs L., et al. “Predictive Learning Enables Neural Networks to Learn Complex Working Memory Tasks.” <i>Proceedings of Machine Learning Research</i>, vol. 199, ML Research Press, 2022, pp. 518–31."},"day":"01","date_updated":"2023-07-18T06:36:28Z","user_id":"2DF688A6-F248-11E8-B48F-1D18A9856A87","acknowledgement":"The authors would like to thank members of the Vogels lab and Manohar lab, as well as Adam Packer, Andrew Saxe, Stefano Sarao Mannelli and Jacob Bakermans for fruitful discussions and comments on earlier versions of the manuscript.\r\nTLvdP was supported by funding from the Biotechnology and Biological Sciences Research Council (BBSRC) [grant number BB/M011224/1]. TPV was supported by an ERC Consolidator Grant (SYNAPSEEK). SGM was funded by a MRC Clinician Scientist Fellowship MR/P00878X and Leverhulme Grant RPG-2018-310.","title":"Predictive learning enables neural networks to learn complex working memory tasks","date_created":"2023-07-16T22:01:12Z","ec_funded":1,"page":"518-531","quality_controlled":"1","oa_version":"Published Version","volume":199,"file":[{"success":1,"creator":"dernst","access_level":"open_access","relation":"main_file","date_updated":"2023-07-18T06:32:38Z","file_size":585135,"file_name":"2022_PMLR_vanderPlas.pdf","content_type":"application/pdf","checksum":"7530a93ef42e10b4db1e5e4b69796e93","date_created":"2023-07-18T06:32:38Z","file_id":"13243"}],"article_processing_charge":"No","publication":"Proceedings of Machine Learning Research","project":[{"_id":"0aacfa84-070f-11eb-9043-d7eb2c709234","name":"Learning the shape of synaptic plasticity rules for neuronal architectures and function through machine learning.","call_identifier":"H2020","grant_number":"819603"}],"publication_identifier":{"eissn":["2640-3498"]},"department":[{"_id":"TiVo"}],"status":"public","publisher":"ML Research Press","intvolume":"       199","author":[{"full_name":"Van Der Plas, Thijs L.","first_name":"Thijs L.","last_name":"Van Der Plas"},{"first_name":"Tim P","last_name":"Vogels","full_name":"Vogels, Tim P","orcid":"0000-0003-3295-6181","id":"CB6FF8D2-008F-11EA-8E08-2637E6697425"},{"first_name":"Sanjay G.","full_name":"Manohar, Sanjay G.","last_name":"Manohar"}],"type":"conference"}