{"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-stigmergy-as-a-computational-memory-in","title":"Using stigmergy as a computational memory in the design of recurrent neural networks","arxiv_id":"1903.01341","date":"2019-01-09","proceeding":null,"authors":["Federico A. Galatolo","Mario G. C. A. Cimino","Gigliola Vaglini"],"abstract":"In this paper, a novel architecture of Recurrent Neural Network (RNN) is\ndesigned and experimented. The proposed RNN adopts a computational memory based\non the concept of stigmergy. The basic principle of a Stigmergic Memory (SM) is\nthat the activity of deposit/removal of a quantity in the SM stimulates the\nnext activities of deposit/removal. Accordingly, subsequent SM activities tend\nto reinforce/weaken each other, generating a coherent coordination between the\nSM activities and the input temporal stimulus. We show that, in a problem of\nsupervised classification, the SM encodes the temporal input in an emergent\nrepresentational model, by coordinating the deposit, removal and classification\nactivities. This study lays down a basic framework for the derivation of a\nSM-RNN. A formal ontology of SM is discussed, and the SM-RNN architecture is\ndetailed. To appreciate the computational power of an SM-RNN, comparative NNs\nhave been selected and trained to solve the MNIST handwritten digits\nrecognition benchmark in its two variants: spatial (sequences of bitmap rows)\nand temporal (sequences of pen strokes).","url_abs":"http://arxiv.org/abs/1903.01341v1","url_pdf":"http://arxiv.org/pdf/1903.01341v1.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-stigmergy-as-a-computational-memory-in","repo_url":"https://github.com/galatolofederico/icpram2019","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"classification","task_name":"General Classification"},{"task_slug":"temporal-sequences","task_name":"Temporal Sequences"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}