{"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-mathematical-formalization-of-hierarchical","title":"A Mathematical Formalization of Hierarchical Temporal Memory's Spatial Pooler","arxiv_id":"1601.06116","date":"2016-01-22","proceeding":null,"authors":["James Mnatzaganian","Ernest Fokoué","Dhireesha Kudithipudi"],"abstract":"Hierarchical temporal memory (HTM) is an emerging machine learning algorithm,\nwith the potential to provide a means to perform predictions on spatiotemporal\ndata. The algorithm, inspired by the neocortex, currently does not have a\ncomprehensive mathematical framework. This work brings together all aspects of\nthe spatial pooler (SP), a critical learning component in HTM, under a single\nunifying framework. The primary learning mechanism is explored, where a maximum\nlikelihood estimator for determining the degree of permanence update is\nproposed. The boosting mechanisms are studied and found to be only relevant\nduring the initial few iterations of the network. Observations are made\nrelating HTM to well-known algorithms such as competitive learning and\nattribute bagging. Methods are provided for using the SP for classification as\nwell as dimensionality reduction. Empirical evidence verifies that given the\nproper parameterizations, the SP may be used for feature learning.","url_abs":"http://arxiv.org/abs/1601.06116v3","url_pdf":"http://arxiv.org/pdf/1601.06116v3.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-mathematical-formalization-of-hierarchical","repo_url":"https://github.com/mrkrynmdsco/htm-python","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":null}],"tasks":[{"task_slug":"attribute","task_name":"Attribute"},{"task_slug":"dimensionality-reduction","task_name":"Dimensionality Reduction"}],"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}