{"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/simnets-a-generalization-of-convolutional","title":"SimNets: A Generalization of Convolutional Networks","arxiv_id":"1410.0781","date":"2014-10-03","proceeding":null,"authors":["Nadav Cohen","Amnon Shashua"],"abstract":"We present a deep layered architecture that generalizes classical\nconvolutional neural networks (ConvNets). The architecture, called SimNets, is\ndriven by two operators, one being a similarity function whose family contains\nthe convolution operator used in ConvNets, and the other is a new soft\nmax-min-mean operator called MEX that realizes classical operators like ReLU\nand max pooling, but has additional capabilities that make SimNets a powerful\ngeneralization of ConvNets. Three interesting properties emerge from the\narchitecture: (i) the basic input to hidden layer to output machinery contains\nas special cases kernel machines with the Exponential and Generalized Gaussian\nkernels, the output units being \"neurons in feature space\" (ii) in its general\nform, the basic machinery has a higher abstraction level than kernel machines,\nand (iii) initializing networks using unsupervised learning is natural.\nExperiments demonstrate the capability of achieving state of the art accuracy\nwith networks that are an order of magnitude smaller than comparable ConvNets.","url_abs":"http://arxiv.org/abs/1410.0781v3","url_pdf":"http://arxiv.org/pdf/1410.0781v3.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":"simnets-a-generalization-of-convolutional","repo_url":"https://github.com/HUJI-Deep/caffe-simnets","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok","spdx":"NOASSERTION"}}],"tasks":[],"methods":[{"method_slug":"convolution","method_name":"Convolution"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1410.0781","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}