{"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-darwin-evolutionary","title":"Deep Learning with Darwin: Evolutionary Synthesis of Deep Neural Networks","arxiv_id":"1606.04393","date":"2016-06-14","proceeding":null,"authors":["Mohammad Javad Shafiee","Akshaya Mishra","Alexander Wong"],"abstract":"Taking inspiration from biological evolution, we explore the idea of \"Can\ndeep neural networks evolve naturally over successive generations into highly\nefficient deep neural networks?\" by introducing the notion of synthesizing new\nhighly efficient, yet powerful deep neural networks over successive generations\nvia an evolutionary process from ancestor deep neural networks. The\narchitectural traits of ancestor deep neural networks are encoded using\nsynaptic probability models, which can be viewed as the `DNA' of these\nnetworks. New descendant networks with differing network architectures are\nsynthesized based on these synaptic probability models from the ancestor\nnetworks and computational environmental factor models, in a random manner to\nmimic heredity, natural selection, and random mutation. These offspring\nnetworks are then trained into fully functional networks, like one would train\na newborn, and have more efficient, more diverse network architectures than\ntheir ancestor networks, while achieving powerful modeling capabilities.\nExperimental results for the task of visual saliency demonstrated that the\nsynthesized `evolved' offspring networks can achieve state-of-the-art\nperformance while having network architectures that are significantly more\nefficient (with a staggering $\\sim$48-fold decrease in synapses by the fourth\ngeneration) compared to the original ancestor network.","url_abs":"http://arxiv.org/abs/1606.04393v3","url_pdf":"http://arxiv.org/pdf/1606.04393v3.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-darwin-evolutionary","repo_url":"https://github.com/joan-teriihoania/algorithme-genetique","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":null}],"tasks":[{"task_slug":"deep-learning","task_name":"Deep Learning"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}