{"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/an-infinite-restricted-boltzmann-machine","title":"An Infinite Restricted Boltzmann Machine","arxiv_id":"1502.02476","date":"2015-02-09","proceeding":null,"authors":["Marc-Alexandre Côté","Hugo Larochelle"],"abstract":"We present a mathematical construction for the restricted Boltzmann machine\n(RBM) that doesn't require specifying the number of hidden units. In fact, the\nhidden layer size is adaptive and can grow during training. This is obtained by\nfirst extending the RBM to be sensitive to the ordering of its hidden units.\nThen, thanks to a carefully chosen definition of the energy function, we show\nthat the limit of infinitely many hidden units is well defined. As with RBM,\napproximate maximum likelihood training can be performed, resulting in an\nalgorithm that naturally and adaptively adds trained hidden units during\nlearning. We empirically study the behaviour of this infinite RBM, showing that\nits performance is competitive to that of the RBM, while not requiring the\ntuning of a hidden layer size.","url_abs":"http://arxiv.org/abs/1502.02476v4","url_pdf":"http://arxiv.org/pdf/1502.02476v4.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":"an-infinite-restricted-boltzmann-machine","repo_url":"https://github.com/MarcCote/iRBM","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}