{"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/using-weight-mirrors-to-improve-feedback","title":"Deep Learning without Weight Transport","arxiv_id":"1904.05391","date":"2019-04-10","proceeding":"NeurIPS 2019 12","authors":["Mohamed Akrout","Collin Wilson","Peter C. Humphreys","Timothy Lillicrap","Douglas Tweed"],"abstract":"Current algorithms for deep learning probably cannot run in the brain because they rely on weight transport, where forward-path neurons transmit their synaptic weights to a feedback path, in a way that is likely impossible biologically. An algorithm called feedback alignment achieves deep learning without weight transport by using random feedback weights, but it performs poorly on hard visual-recognition tasks. Here we describe two mechanisms - a neural circuit called a weight mirror and a modification of an algorithm proposed by Kolen and Pollack in 1994 - both of which let the feedback path learn appropriate synaptic weights quickly and accurately even in large networks, without weight transport or complex wiring.Tested on the ImageNet visual-recognition task, these mechanisms outperform both feedback alignment and the newer sign-symmetry method, and nearly match backprop, the standard algorithm of deep learning, which uses weight transport.","url_abs":"https://arxiv.org/abs/1904.05391v5","url_pdf":"https://arxiv.org/pdf/1904.05391v5.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":"using-weight-mirrors-to-improve-feedback","repo_url":"https://github.com/makrout/Deep-Learning-without-Weight-Transport","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok"}},{"paper_slug":"using-weight-mirrors-to-improve-feedback","repo_url":"https://github.com/nasiryahm/STDWI","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok"}},{"paper_slug":"using-weight-mirrors-to-improve-feedback","repo_url":"https://github.com/prashanth-prakash/Autoencode-using-weight-mirrors","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok"}}],"tasks":[{"task_slug":"deep-learning","task_name":"Deep Learning"}],"methods":[{"method_slug":"kp","method_name":"KP"}],"datasets_introduced":[],"methods_introduced":[{"slug":"kp","name":"KP","full_name":"Kollen-Pollack Learning"}],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1904.05391","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}