Active inference and artificial curiosity
Karl J. Friston Director, Wellcome Centre for Human Neuroimaging Institute of Neurology, UCL London
10:30 am Thursday, December 8
Zoom: https://uqam.zoom.us/j/88481835073
Cognitive Informatics Seminar Séminaire en informatique cognitive UQÀM ISC DIC CRIA
Abstract: This talk offers a formal account of insight and learning in terms of active (Bayesian) inference. It deals with the dual problem of inferring states of the world and learning its statistical structure. In contrast to current trends in machine learning (e.g., deep learning), we focus on how agents learn from a small number of ambiguous outcomes to form insight. I will use simulations of abstract rule-learning and approximate Bayesian inference to show that minimising (expected) free energy leads to active sampling of novel contingencies. This epistemic, curiosity-directed behaviour closes `explanatory gaps' in knowledge about the causal structure of the world, thereby reducing ignorance, in addition to resolving uncertainty about states of the known world. We then move from inference to model selection or structure learning to show how abductive processes emerge when agents test plausible hypotheses about symmetries in their generative models of the world. The ensuing Bayesian model reduction evokes mechanisms associated with sleep and has all the hallmarks of aha moments. [A person with his hand on his chin Description automatically generated with medium confidence] Karl Friston, theoretical neuroscientist and authority on brain imaging, invented statistical parametric mapping (SPM), voxel-based morphometry (VBM) and dynamic causal modelling (DCM). Mathematical contributions include variational Laplacian procedures and generalized filtering for hierarchical Bayesian model inversion. Friston currently works on models of functional integration in the human brain and the principles that underlie neuronal interactions. His main contribution to theoretical neurobiology is a free-energy principle for action and perception (active inference).
A repository of active inference papers: GitHub - BerenMillidge/FEP_Active_Inference_Papers: A repository for major/influential FEP and active inference papers.https://eur03.safelinks.protection.outlook.com/?url=https%3A%2F%2Fgithub.com%2FBerenMillidge%2FFEP_Active_Inference_Papers&data=05%7C01%7Charnad%40ecs.soton.ac.uk%7Cb6f3660d23764b9ee8eb08da748f18a4%7C4a5378f929f44d3ebe89669d03ada9d8%7C0%7C0%7C637950455201307338%7CUnknown%7CTWFpbGZsb3d8eyJWIjoiMC4wLjAwMDAiLCJQIjoiV2luMzIiLCJBTiI6Ik1haWwiLCJXVCI6Mn0%3D%7C3000%7C%7C%7C&sdata=DtNtiNM0g5mRIRYi%2B3XaxQtPeArdxjAMDmjuQEqRBjM%3D&reserved=0 Theoretical lecture on the physics behind active inference: I am therefore I think by Karl Friston - YouTubehttps://eur03.safelinks.protection.outlook.com/?url=https%3A%2F%2Fwww.youtube.com%2Fwatch%3Fv%3DJVqQJTFfFC8&data=05%7C01%7Charnad%40ecs.soton.ac.uk%7Cb6f3660d23764b9ee8eb08da748f18a4%7C4a5378f929f44d3ebe89669d03ada9d8%7C0%7C0%7C637950455201307338%7CUnknown%7CTWFpbGZsb3d8eyJWIjoiMC4wLjAwMDAiLCJQIjoiV2luMzIiLCJBTiI6Ik1haWwiLCJXVCI6Mn0%3D%7C3000%7C%7C%7C&sdata=XzbZnKGzrGw07bhjjgmY7dPTiRwQ7yHP7yD3RG9XI6c%3D&reserved=0
Sensorimotor Interaction of Language and Symbol Embodiment
Xavier HINAUThttps://www.xavierhinaut.com/ Inriahttps://www.inria.fr/en, Bordeauxhttps://www.google.com/url?q=https%3A%2F%2Fwww.openstreetmap.org%2Frelation%2F105270%23map%3D12%2F44.8313%2F-0.6032&sa=D&sntz=1&usg=AOvVaw3EwHLM1ijHKF8sftXz3YQ1
UQÀM ISC DIC CRIA Séminaire en informatique cognitive/Cognitive Informatics Seminar
Thursday, 10:30 am (EST) January 12, 2023 Zoom **new**: https://uqam.zoom.us/j/89902403751https://eur03.safelinks.protection.outlook.com/?url=https%3A%2F%2Fuqam.zoom.us%2Fj%2F89902403751&data=05%7C01%7Charnad%40ecs.soton.ac.uk%7Cfc38b4e7ba354122a6c708daf31d49f2%7C4a5378f929f44d3ebe89669d03ada9d8%7C0%7C0%7C638089604377408492%7CUnknown%7CTWFpbGZsb3d8eyJWIjoiMC4wLjAwMDAiLCJQIjoiV2luMzIiLCJBTiI6Ik1haWwiLCJXVCI6Mn0%3D%7C3000%7C%7C%7C&sdata=oH%2FCWMA%2BvUINRP7LM74T3kSbnh5on0AphicTUu2rcTg%3D&reserved=0 Abstract: Language involves several hierarchical levels of abstraction. Most models focus on a particular level of abstraction, making them unable to model bottom-up and top-down processes. It is not yet known how the brain grounds symbols to perceptions and how these symbols emerge throughout development. Experimental evidence suggests that perception and action shape one another (e.g., motor areas activated during speech perception) but the precise mechanisms involved in this action-perception shaping at various levels of abstraction are still largely unknown. My work includes modelling language comprehension, language acquisition from a robotic perspective, sensorimotor function and extended models of Reservoir Computing. I will also present general results on reservoir computing, and why it is an interesting framework to model cognitive processes, such as working memory.
[A picture containing person, automaton, tableware Description automatically generated]Xavier Hinaut is a Researcher in the Mnemosyne teamhttps://www.google.com/url?q=https%3A%2F%2Fteam.inria.fr%2Fmnemosyne%2F&sa=D&sntz=1&usg=AOvVaw0ZsOnv5Ou3wKIMgM6y4q3y at https://www.google.com/url?q=https%3A%2F%2Fwww.inria.fr%2Fen%2F&sa=D&sntz=1&usg=AOvVaw2Ik6_oMTuI-iwn08VJKU90 Inriahttps://www.google.com/url?q=https%3A%2F%2Fwww.inria.fr%2Fen%2F&sa=D&sntz=1&usg=AOvVaw2Ik6_oMTuI-iwn08VJKU90 in Bordeauxhttps://www.google.com/url?q=https%3A%2F%2Fwww.openstreetmap.org%2Frelation%2F105270%23map%3D12%2F44.8313%2F-0.6032&sa=D&sntz=1&usg=AOvVaw3EwHLM1ijHKF8sftXz3YQ1. His work focusses mainly on Recurrent Neural Network modelling (especially prefrontal cortex), language acquisition (applied to Robotics) and the brain codes of bird song syntax. The common thread is the neural coding and the modelling of complex sequence processing, “chunking,” learning and production, for “syntax-based” sequences, to be applied to robotics (for eventual embodiment). He manages the development of a new Reservoir Computing library in Python: https://github.com/reservoirpy/reservoirpy
Références
Trouvain, N., Rougier, N., & Hinaut, X. (2022). Create Efficient and Complex Reservoir Computing Architectures with ReservoirPyhttps://hal.inria.fr/hal-03761440/document. In International Conference on Simulation of Adaptive Behavior, pp. 91-102. Pagliarini, S., Leblois, A., & Hinaut, X. (2021). Canary Vocal Sensorimotor Model with RNN Decoder and Low-dimensional GAN Generatorhttps://hal.inria.fr/hal-03482372/document. In 2021 IEEE International Conference on Development and Learning (ICDL), pp. 1-8. Pagliarini, S., Leblois, A., & Hinaut, X. (2020). Vocal imitation in sensorimotor learning models: a comparative review.https://hal.inria.fr/hal-02317144/file/PagliariniLebloisHinaut2020_Review_IEEE_TCDS.pdf IEEE Transactions on Cognitive and Developmental Systems, 13(2), 326-342. Strock, A., Hinaut, X., & Rougier, N. P. (2020). A robust model of gated working memoryhttps://www.biorxiv.org/content/10.1101/589564.full.pdf. Neural Computation, 32(1), 153-181. Hinaut, X., & Dominey, P. F. (2013). Real-time parallel processing of grammatical structure in the fronto-striatal system: A recurrent network simulation study using reservoir computinghttps://journals.plos.org/plosone/article?id=10.1371/journal.pone.0052946. PloS one, 8(2), e52946.