{"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/a-hebbiananti-hebbian-network-derived-from","title":"A Hebbian/Anti-Hebbian Network Derived from Online Non-Negative Matrix Factorization Can Cluster and Discover Sparse Features","arxiv_id":"1503.00680","date":"2015-03-02","proceeding":null,"authors":["Cengiz Pehlevan","Dmitri B. Chklovskii"],"abstract":"Despite our extensive knowledge of biophysical properties of neurons, there\nis no commonly accepted algorithmic theory of neuronal function. Here we\nexplore the hypothesis that single-layer neuronal networks perform online\nsymmetric nonnegative matrix factorization (SNMF) of the similarity matrix of\nthe streamed data. By starting with the SNMF cost function we derive an online\nalgorithm, which can be implemented by a biologically plausible network with\nlocal learning rules. We demonstrate that such network performs soft clustering\nof the data as well as sparse feature discovery. The derived algorithm\nreplicates many known aspects of sensory anatomy and biophysical properties of\nneurons including unipolar nature of neuronal activity and synaptic weights,\nlocal synaptic plasticity rules and the dependence of learning rate on\ncumulative neuronal activity. Thus, we make a step towards an algorithmic\ntheory of neuronal function, which should facilitate large-scale neural circuit\nsimulations and biologically inspired artificial intelligence.","url_abs":"http://arxiv.org/abs/1503.00680v1","url_pdf":"http://arxiv.org/pdf/1503.00680v1.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":"a-hebbiananti-hebbian-network-derived-from","repo_url":"https://github.com/AishwaryaSeth/clustering_snmf","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok"}},{"paper_slug":"a-hebbiananti-hebbian-network-derived-from","repo_url":"https://github.com/miyosuda/snmf","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok","spdx":"Apache-2.0"}}],"tasks":[{"task_slug":"anatomy","task_name":"Anatomy"},{"task_slug":"clustering","task_name":"Clustering"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/1503.00680","atlas_url":"https://app.syntology.ai/?focus=1503.00680","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}