{"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/evolutionary-neural-automl-for-deep-learning","title":"Evolutionary Neural AutoML for Deep Learning","arxiv_id":"1902.06827","date":"2019-02-18","proceeding":null,"authors":["Jason Liang","Elliot Meyerson","Babak Hodjat","Dan Fink","Karl Mutch","Risto Miikkulainen"],"abstract":"Deep neural networks (DNNs) have produced state-of-the-art results in many\nbenchmarks and problem domains. However, the success of DNNs depends on the\nproper configuration of its architecture and hyperparameters. Such a\nconfiguration is difficult and as a result, DNNs are often not used to their\nfull potential. In addition, DNNs in commercial applications often need to\nsatisfy real-world design constraints such as size or number of parameters. To\nmake configuration easier, automatic machine learning (AutoML) systems for deep\nlearning have been developed, focusing mostly on optimization of\nhyperparameters.\n  This paper takes AutoML a step further. It introduces an evolutionary AutoML\nframework called LEAF that not only optimizes hyperparameters but also network\narchitectures and the size of the network. LEAF makes use of both\nstate-of-the-art evolutionary algorithms (EAs) and distributed computing\nframeworks. Experimental results on medical image classification and natural\nlanguage analysis show that the framework can be used to achieve\nstate-of-the-art performance. In particular, LEAF demonstrates that\narchitecture optimization provides a significant boost over hyperparameter\noptimization, and that networks can be minimized at the same time with little\ndrop in performance. LEAF therefore forms a foundation for democratizing and\nimproving AI, as well as making AI practical in future applications.","url_abs":"http://arxiv.org/abs/1902.06827v3","url_pdf":"http://arxiv.org/pdf/1902.06827v3.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":"evolutionary-neural-automl-for-deep-learning","repo_url":"https://github.com/lucylow/Covid_Control","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok","spdx":"Apache-2.0"}}],"tasks":[{"task_slug":"automl","task_name":"AutoML"},{"task_slug":"deep-learning","task_name":"Deep Learning"},{"task_slug":"distributed-computing","task_name":"Distributed Computing"},{"task_slug":"evolutionary-algorithms","task_name":"Evolutionary Algorithms"},{"task_slug":"hyperparameter-optimization","task_name":"Hyperparameter Optimization"},{"task_slug":"image-classification","task_name":"Image Classification"},{"task_slug":"medical-image-classification","task_name":"Medical Image Classification"},{"task_slug":"architecture-search","task_name":"Neural Architecture Search"},{"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}