{"pk":27596,"title":"Anticipatory Active Inference from Learned Recurrent Neural Forward Models","subtitle":null,"abstract":"We demonstrate that inference-based goal-directed behavior can be done by utilizing the temporal gradients in re-current neural network (RNN). The RNN learns a dynamic sensorimotor forward model. Once the RNN is trained, it can beused to execute active-inference-based, goal-directed policy optimization. The internal neural activities of the trained RNNessentially model the predictive state of the controlled entity. The implemented optimization process projects the neural activ-ities into the future via the RNN recurrences following a tentative sequence of motor commands (encoded in neurons akin torecurrent parametric biases). This sequence is adapted by back-projecting the error between the forward-projected hypotheticalstates and desired (goal-like) system states onto the motor commands. Few cycles of forward projection and goal-based errorbackpropagation yield the sequences of motor commands that control the dynamical systems. As an example, we show that atrained RNN model can be used to effectively control a quadrocopter-like system.","language":"eng","license":{"name":"","short_name":"","text":null,"url":""},"keywords":[],"section":"Posters: Member Abstracts","is_remote":true,"remote_url":"https://escholarship.org/uc/item/0mz9w75s","frozenauthors":[{"first_name":"Sebastian","middle_name":"","last_name":"Otte","name_suffix":"","institution":"University of T ̈ubingen","department":""},{"first_name":"Theresa","middle_name":"","last_name":"Schmitt","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/27596/galley/17232/download/"}]}