{"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/practical-recommendations-for-gradient-based","title":"Practical recommendations for gradient-based training of deep architectures","arxiv_id":"1206.5533","date":"2012-06-24","proceeding":null,"authors":["Yoshua Bengio"],"abstract":"Learning algorithms related to artificial neural networks and in particular\nfor Deep Learning may seem to involve many bells and whistles, called\nhyper-parameters. This chapter is meant as a practical guide with\nrecommendations for some of the most commonly used hyper-parameters, in\nparticular in the context of learning algorithms based on back-propagated\ngradient and gradient-based optimization. It also discusses how to deal with\nthe fact that more interesting results can be obtained when allowing one to\nadjust many hyper-parameters. Overall, it describes elements of the practice\nused to successfully and efficiently train and debug large-scale and often deep\nmulti-layer neural networks. It closes with open questions about the training\ndifficulties observed with deeper architectures.","url_abs":"http://arxiv.org/abs/1206.5533v2","url_pdf":"http://arxiv.org/pdf/1206.5533v2.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":"practical-recommendations-for-gradient-based","repo_url":"https://github.com/Robinatp/Tensorflow_Model_Inception","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok"}},{"paper_slug":"practical-recommendations-for-gradient-based","repo_url":"https://github.com/Xilinx/xilinx-tiny-cnn","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok"}},{"paper_slug":"practical-recommendations-for-gradient-based","repo_url":"https://github.com/YukiDaSlayer316/R-Tutorial","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok"}},{"paper_slug":"practical-recommendations-for-gradient-based","repo_url":"https://github.com/canbyjiaoxun/DAC2019-TCAM","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok","spdx":"NOASSERTION"}},{"paper_slug":"practical-recommendations-for-gradient-based","repo_url":"https://github.com/dl-nlp/dl-nlp.github.io","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"unanswered"}},{"paper_slug":"practical-recommendations-for-gradient-based","repo_url":"https://github.com/marcelsheeny/tiny-dnn-snn","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok","spdx":"NOASSERTION"}},{"paper_slug":"practical-recommendations-for-gradient-based","repo_url":"https://github.com/micahpearlman/tiny-cnn","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok"}},{"paper_slug":"practical-recommendations-for-gradient-based","repo_url":"https://github.com/nyanp/tiny-cnn","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok","spdx":"NOASSERTION"}},{"paper_slug":"practical-recommendations-for-gradient-based","repo_url":"https://github.com/sagpant/tiny-dnn","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok","spdx":"NOASSERTION"}},{"paper_slug":"practical-recommendations-for-gradient-based","repo_url":"https://github.com/suhubdy/nabla","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok","spdx":"NOASSERTION"}},{"paper_slug":"practical-recommendations-for-gradient-based","repo_url":"https://github.com/tensorflow/models","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":null},{"paper_slug":"practical-recommendations-for-gradient-based","repo_url":"https://github.com/tensorflow/models/tree/master/research/inception","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":null},{"paper_slug":"practical-recommendations-for-gradient-based","repo_url":"https://github.com/tiny-dnn/tiny-dnn","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok","spdx":"NOASSERTION"}},{"paper_slug":"practical-recommendations-for-gradient-based","repo_url":"https://github.com/yukikongju/R-Tutorial","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok"}}],"tasks":[],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1206.5533","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}