{"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/dropneuron-simplifying-the-structure-of-deep","title":"DropNeuron: Simplifying the Structure of Deep Neural Networks","arxiv_id":"1606.07326","date":"2016-06-23","proceeding":null,"authors":["Wei Pan","Hao Dong","Yike Guo"],"abstract":"Deep learning using multi-layer neural networks (NNs) architecture manifests\nsuperb power in modern machine learning systems. The trained Deep Neural\nNetworks (DNNs) are typically large. The question we would like to address is\nwhether it is possible to simplify the NN during training process to achieve a\nreasonable performance within an acceptable computational time. We presented a\nnovel approach of optimising a deep neural network through regularisation of\nnet- work architecture. We proposed regularisers which support a simple\nmechanism of dropping neurons during a network training process. The method\nsupports the construction of a simpler deep neural networks with compatible\nperformance with its simplified version. As a proof of concept, we evaluate the\nproposed method with examples including sparse linear regression, deep\nautoencoder and convolutional neural network. The valuations demonstrate\nexcellent performance.\n  The code for this work can be found in\nhttp://www.github.com/panweihit/DropNeuron","url_abs":"http://arxiv.org/abs/1606.07326v3","url_pdf":"http://arxiv.org/pdf/1606.07326v3.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":"dropneuron-simplifying-the-structure-of-deep","repo_url":"https://github.com/panweihit/DropNeuron","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"tf","reach":null}],"tasks":[],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":null,"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}