{"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/spectrum-diverse-neuroevolution-with-unified","title":"Spectrum-Diverse Neuroevolution with Unified Neural Models","arxiv_id":"1902.06703","date":"2019-01-06","proceeding":null,"authors":["Danilo Vasconcellos Vargas","Junichi Murata"],"abstract":"Learning algorithms are being increasingly adopted in various applications.\nHowever, further expansion will require methods that work more automatically.\nTo enable this level of automation, a more powerful solution representation is\nneeded. However, by increasing the representation complexity a second problem\narises. The search space becomes huge and therefore an associated scalable and\nefficient searching algorithm is also required. To solve both problems, first a\npowerful representation is proposed that unifies most of the neural networks\nfeatures from the literature into one representation. Secondly, a new diversity\npreserving method called Spectrum Diversity is created based on the new concept\nof chromosome spectrum that creates a spectrum out of the characteristics and\nfrequency of alleles in a chromosome. The combination of Spectrum Diversity\nwith a unified neuron representation enables the algorithm to either surpass or\nequal NeuroEvolution of Augmenting Topologies (NEAT) on all of the five classes\nof problems tested. Ablation tests justifies the good results, showing the\nimportance of added new features in the unified neuron representation. Part of\nthe success is attributed to the novelty-focused evolution and good scalability\nwith chromosome size provided by Spectrum Diversity. Thus, this study sheds\nlight on a new representation and diversity preserving mechanism that should\nimpact algorithms and applications to come.\n  To download the code please access the following\nhttps://github.com/zweifel/Physis-Shard.","url_abs":"http://arxiv.org/abs/1902.06703v1","url_pdf":"http://arxiv.org/pdf/1902.06703v1.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":"spectrum-diverse-neuroevolution-with-unified","repo_url":"https://github.com/zweifel/Physis-Shard","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"none","reach":null}],"tasks":[{"task_slug":"diversity","task_name":"Diversity"}],"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}