{"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/neural-networks-regularization-through-class","title":"Neural Networks Regularization Through Class-wise Invariant Representation Learning","arxiv_id":"1709.01867","date":"2017-09-06","proceeding":null,"authors":["Soufiane Belharbi","Clément Chatelain","Romain Hérault","Sébastien Adam"],"abstract":"Training deep neural networks is known to require a large number of training\nsamples. However, in many applications only few training samples are available.\nIn this work, we tackle the issue of training neural networks for\nclassification task when few training samples are available. We attempt to\nsolve this issue by proposing a new regularization term that constrains the\nhidden layers of a network to learn class-wise invariant representations. In\nour regularization framework, learning invariant representations is generalized\nto the class membership where samples with the same class should have the same\nrepresentation. Numerical experiments over MNIST and its variants showed that\nour proposal helps improving the generalization of neural network particularly\nwhen trained with few samples. We provide the source code of our framework\nhttps://github.com/sbelharbi/learning-class-invariant-features .","url_abs":"http://arxiv.org/abs/1709.01867v4","url_pdf":"http://arxiv.org/pdf/1709.01867v4.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":"neural-networks-regularization-through-class","repo_url":"https://github.com/sbelharbi/learning-class-invariant-features","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"none","reach":null}],"tasks":[{"task_slug":"classification","task_name":"General Classification"},{"task_slug":"representation-learning","task_name":"Representation Learning"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}