{"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/dataflow-matrix-machines-as-programmable","title":"Dataflow matrix machines as programmable, dynamically expandable, self-referential generalized recurrent neural networks","arxiv_id":"1605.05296","date":"2016-05-17","proceeding":null,"authors":["Michael Bukatin","Steve Matthews","Andrey Radul"],"abstract":"Dataflow matrix machines are a powerful generalization of recurrent neural\nnetworks. They work with multiple types of linear streams and multiple types of\nneurons, including higher-order neurons which dynamically update the matrix\ndescribing weights and topology of the network in question while the network is\nrunning. It seems that the power of dataflow matrix machines is sufficient for\nthem to be a convenient general purpose programming platform. This paper\nexplores a number of useful programming idioms and constructions arising in\nthis context.","url_abs":"http://arxiv.org/abs/1605.05296v2","url_pdf":"http://arxiv.org/pdf/1605.05296v2.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":"dataflow-matrix-machines-as-programmable","repo_url":"https://github.com/anhinga/fluid","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}