{"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/superspike-supervised-learning-in-multi-layer","title":"SuperSpike: Supervised learning in multi-layer spiking neural networks","arxiv_id":"1705.11146","date":"2017-05-31","proceeding":null,"authors":["Friedemann Zenke","Surya Ganguli"],"abstract":"A vast majority of computation in the brain is performed by spiking neural\nnetworks. Despite the ubiquity of such spiking, we currently lack an\nunderstanding of how biological spiking neural circuits learn and compute\nin-vivo, as well as how we can instantiate such capabilities in artificial\nspiking circuits in-silico. Here we revisit the problem of supervised learning\nin temporally coding multi-layer spiking neural networks. First, by using a\nsurrogate gradient approach, we derive SuperSpike, a nonlinear voltage-based\nthree factor learning rule capable of training multi-layer networks of\ndeterministic integrate-and-fire neurons to perform nonlinear computations on\nspatiotemporal spike patterns. Second, inspired by recent results on feedback\nalignment, we compare the performance of our learning rule under different\ncredit assignment strategies for propagating output errors to hidden units.\nSpecifically, we test uniform, symmetric and random feedback, finding that\nsimpler tasks can be solved with any type of feedback, while more complex tasks\nrequire symmetric feedback. In summary, our results open the door to obtaining\na better scientific understanding of learning and computation in spiking neural\nnetworks by advancing our ability to train them to solve nonlinear problems\ninvolving transformations between different spatiotemporal spike-time patterns.","url_abs":"http://arxiv.org/abs/1705.11146v2","url_pdf":"http://arxiv.org/pdf/1705.11146v2.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":"superspike-supervised-learning-in-multi-layer","repo_url":"https://github.com/lsying009/FS_coding","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"unanswered"}}],"tasks":[],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":null,"atlas_url":"https://app.syntology.ai/?focus=1705.11146","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}