{"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/automated-search-for-configurations-of-deep","title":"Automated Search for Configurations of Deep Neural Network Architectures","arxiv_id":"1904.04612","date":"2019-04-09","proceeding":null,"authors":["Salah Ghamizi","Maxime Cordy","Mike Papadakis","Yves Le Traon"],"abstract":"Deep Neural Networks (DNNs) are intensively used to solve a wide variety of\ncomplex problems. Although powerful, such systems require manual configuration\nand tuning. To this end, we view DNNs as configurable systems and propose an\nend-to-end framework that allows the configuration, evaluation and automated\nsearch for DNN architectures. Therefore, our contribution is threefold. First,\nwe model the variability of DNN architectures with a Feature Model (FM) that\ngeneralizes over existing architectures. Each valid configuration of the FM\ncorresponds to a valid DNN model that can be built and trained. Second, we\nimplement, on top of Tensorflow, an automated procedure to deploy, train and\nevaluate the performance of a configured model. Third, we propose a method to\nsearch for configurations and demonstrate that it leads to good DNN models. We\nevaluate our method by applying it on image classification tasks (MNIST,\nCIFAR-10) and show that, with limited amount of computation and training, our\nmethod can identify high-performing architectures (with high accuracy). We also\ndemonstrate that we outperform existing state-of-the-art architectures\nhandcrafted by ML researchers. Our FM and framework have been released %and are\npublicly available to support replication and future research.","url_abs":"http://arxiv.org/abs/1904.04612v1","url_pdf":"http://arxiv.org/pdf/1904.04612v1.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":"automated-search-for-configurations-of-deep","repo_url":"https://github.com/yamizi/FeatureNet","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"tf","reach":null}],"tasks":[{"task_slug":"image-classification","task_name":"Image Classification"},{"task_slug":"image-classification","task_name":"image-classification"},{"task_slug":null,"task_name":"valid"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}