{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/non-linear-motor-control-by-local-learning-in","title":"Non-linear motor control by local learning in spiking neural networks","arxiv_id":"1712.10158","date":"2017-12-29","proceeding":"ICML 2018 7","authors":["Aditya Gilra","Wulfram Gerstner"],"abstract":"Learning weights in a spiking neural network with hidden neurons, using\nlocal, stable and online rules, to control non-linear body dynamics is an open\nproblem. Here, we employ a supervised scheme, Feedback-based Online Local\nLearning Of Weights (FOLLOW), to train a network of heterogeneous spiking\nneurons with hidden layers, to control a two-link arm so as to reproduce a\ndesired state trajectory. The network first learns an inverse model of the\nnon-linear dynamics, i.e. from state trajectory as input to the network, it\nlearns to infer the continuous-time command that produced the trajectory.\nConnection weights are adjusted via a local plasticity rule that involves\npre-synaptic firing and post-synaptic feedback of the error in the inferred\ncommand. We choose a network architecture, termed differential feedforward,\nthat gives the lowest test error from different feedforward and recurrent\narchitectures. The learned inverse model is then used to generate a\ncontinuous-time motor command to control the arm, given a desired trajectory.","url_abs":"http://arxiv.org/abs/1712.10158v1","url_pdf":"http://arxiv.org/pdf/1712.10158v1.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"non-linear-motor-control-by-local-learning-in","repo_url":"https://github.com/adityagilra/FOLLOWControl","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":null}],"tasks":[],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}