{"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/deep-learning-with-eigenvalue-decay","title":"Deep Learning with Eigenvalue Decay Regularizer","arxiv_id":"1604.06985","date":"2016-04-24","proceeding":null,"authors":["Oswaldo Ludwig"],"abstract":"This paper extends our previous work on regularization of neural networks\nusing Eigenvalue Decay by employing a soft approximation of the dominant\neigenvalue in order to enable the calculation of its derivatives in relation to\nthe synaptic weights, and therefore the application of back-propagation, which\nis a primary demand for deep learning. Moreover, we extend our previous\ntheoretical analysis to deep neural networks and multiclass classification\nproblems. Our method is implemented as an additional regularizer in Keras, a\nmodular neural networks library written in Python, and evaluated in the\nbenchmark data sets Reuters Newswire Topics Classification, IMDB database for\nbinary sentiment classification, MNIST database of handwritten digits and\nCIFAR-10 data set for image classification.","url_abs":"http://arxiv.org/abs/1604.06985v3","url_pdf":"http://arxiv.org/pdf/1604.06985v3.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":"deep-learning-with-eigenvalue-decay","repo_url":"https://github.com/oswaldoludwig/Eigenvalue-Decay-Regularizer-for-Keras","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"tf","reach":null}],"tasks":[{"task_slug":"classification-1","task_name":"Classification"},{"task_slug":"deep-learning","task_name":"Deep Learning"},{"task_slug":"classification","task_name":"General Classification"},{"task_slug":"image-classification","task_name":"Image Classification"},{"task_slug":"sentiment-analysis","task_name":"Sentiment Analysis"},{"task_slug":"sentiment-classification","task_name":"Sentiment Classification"},{"task_slug":"image-classification","task_name":"image-classification"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}