{"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/gaussian-binary-restricted-boltzmann-machines","title":"Gaussian-binary Restricted Boltzmann Machines on Modeling Natural Image Statistics","arxiv_id":"1401.5900","date":"2014-01-23","proceeding":null,"authors":["Nan Wang","Jan Melchior","Laurenz Wiskott"],"abstract":"We present a theoretical analysis of Gaussian-binary restricted Boltzmann\nmachines (GRBMs) from the perspective of density models. The key aspect of this\nanalysis is to show that GRBMs can be formulated as a constrained mixture of\nGaussians, which gives a much better insight into the model's capabilities and\nlimitations. We show that GRBMs are capable of learning meaningful features\nboth in a two-dimensional blind source separation task and in modeling natural\nimages. Further, we show that reported difficulties in training GRBMs are due\nto the failure of the training algorithm rather than the model itself. Based on\nour analysis we are able to propose several training recipes, which allowed\nsuccessful and fast training in our experiments. Finally, we discuss the\nrelationship of GRBMs to several modifications that have been proposed to\nimprove the model.","url_abs":"http://arxiv.org/abs/1401.5900v1","url_pdf":"http://arxiv.org/pdf/1401.5900v1.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":"gaussian-binary-restricted-boltzmann-machines","repo_url":"https://github.com/MelJan/PyDeep","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok"}}],"tasks":[{"task_slug":"blind-source-separation","task_name":"blind source separation"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1401.5900","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}