{"pk":27629,"title":"Learning Temporal Generative Neural Codes for Biological Motion Perceptionand Inference","subtitle":null,"abstract":"We introduce a modular recurrent neural architecture, which learns distributed, generative temporal models of bio-logical motion. It encodes modal visual and proprioceptive (angular) biological motions separately by means of autoencoders,structuring respective postures, motion directions, and motion magnitudes separately. The submodal encoders are interdepen-dent by predicting each other’s next autoencoder states temporally. As a result, distributed attractor states can develop fromself-generated motions. We show that the architecture is able to synchronize its activities across modalities towards overallconsistent action-encoding attractors. Moreover, the developing spatial and temporal structures can complete partially observ-able actions, e.g., when only providing visual information. Furthermore, we show that the network is capable of simulatingwhole-body actions without any sensory stimulation, thus imagining unfolding actions. Finally, we show that the network isable to infer the visual perspective on a biological motion. Thus, the neural architecture enables embodied perspective takingand action inference.","language":"eng","license":{"name":"","short_name":"","text":null,"url":""},"keywords":[],"section":"Posters: Member Abstracts","is_remote":true,"remote_url":"https://escholarship.org/uc/item/6c76q60r","frozenauthors":[{"first_name":"Fabian","middle_name":"","last_name":"Schrodt","name_suffix":"","institution":"University of T ̈ubingen","department":""},{"first_name":"Martin","middle_name":"V.","last_name":"Butz","name_suffix":"","institution":"University of T ̈ubingen","department":""}],"date_submitted":null,"date_accepted":null,"date_published":"2017-01-01T18:00:00Z","render_galley":null,"galleys":[{"label":"PDF","type":"pdf","path":"https://journalpub.escholarship.org/cognitivesciencesociety/article/27629/galley/17265/download/"}]}