{"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-and-v-values-a","title":"Dataflow Matrix Machines and V-values: a Bridge between Programs and Neural Nets","arxiv_id":"1712.07447","date":"2017-12-20","proceeding":null,"authors":["Michael Bukatin","Jon Anthony"],"abstract":"1) Dataflow matrix machines (DMMs) generalize neural nets by replacing\nstreams of numbers with linear streams (streams supporting linear\ncombinations), allowing arbitrary input and output arities for activation\nfunctions, countable-sized networks with finite dynamically changeable active\npart capable of unbounded growth, and a very expressive self-referential\nmechanism.\n  2) DMMs are suitable for general-purpose programming, while retaining the key\nproperty of recurrent neural networks: programs are expressed via matrices of\nreal numbers, and continuous changes to those matrices produce arbitrarily\nsmall variations in the associated programs.\n  3) Spaces of V-values (vector-like elements based on nested maps) are\nparticularly useful, enabling DMMs with variadic activation functions and\nconveniently representing conventional data structures.","url_abs":"http://arxiv.org/abs/1712.07447v2","url_pdf":"http://arxiv.org/pdf/1712.07447v2.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-and-v-values-a","repo_url":"https://github.com/jsa-aerial/DMM","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"none","reach":null}],"tasks":[],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":null,"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}