{"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/training-binary-multilayer-neural-networks","title":"Training Binary Multilayer Neural Networks for Image Classification using Expectation Backpropagation","arxiv_id":"1503.03562","date":"2015-03-12","proceeding":null,"authors":["Zhiyong Cheng","Daniel Soudry","Zexi Mao","Zhenzhong Lan"],"abstract":"Compared to Multilayer Neural Networks with real weights, Binary Multilayer\nNeural Networks (BMNNs) can be implemented more efficiently on dedicated\nhardware. BMNNs have been demonstrated to be effective on binary classification\ntasks with Expectation BackPropagation (EBP) algorithm on high dimensional text\ndatasets. In this paper, we investigate the capability of BMNNs using the EBP\nalgorithm on multiclass image classification tasks. The performances of binary\nneural networks with multiple hidden layers and different numbers of hidden\nunits are examined on MNIST. We also explore the effectiveness of image spatial\nfilters and the dropout technique in BMNNs. Experimental results on MNIST\ndataset show that EBP can obtain 2.12% test error with binary weights and 1.66%\ntest error with real weights, which is comparable to the results of standard\nBackPropagation algorithm on fully connected MNNs.","url_abs":"http://arxiv.org/abs/1503.03562v3","url_pdf":"http://arxiv.org/pdf/1503.03562v3.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":"training-binary-multilayer-neural-networks","repo_url":"https://github.com/ExpectationBackpropagation/EBP_Matlab_Code","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok"}}],"tasks":[{"task_slug":"binary-classification","task_name":"Binary Classification"},{"task_slug":"classification","task_name":"General Classification"},{"task_slug":"image-classification","task_name":"Image Classification"},{"task_slug":"image-classification","task_name":"image-classification"}],"methods":[{"method_slug":"dropout","method_name":"Dropout"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1503.03562","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}