{"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/stopping-gan-violence-generative","title":"Stopping GAN Violence: Generative Unadversarial Networks","arxiv_id":"1703.02528","date":"2017-03-07","proceeding":null,"authors":["Samuel Albanie","Sébastien Ehrhardt","João F. Henriques"],"abstract":"While the costs of human violence have attracted a great deal of attention\nfrom the research community, the effects of the network-on-network (NoN)\nviolence popularised by Generative Adversarial Networks have yet to be\naddressed. In this work, we quantify the financial, social, spiritual,\ncultural, grammatical and dermatological impact of this aggression and address\nthe issue by proposing a more peaceful approach which we term Generative\nUnadversarial Networks (GUNs). Under this framework, we simultaneously train\ntwo models: a generator G that does its best to capture whichever data\ndistribution it feels it can manage, and a motivator M that helps G to achieve\nits dream. Fighting is strictly verboten and both models evolve by learning to\nrespect their differences. The framework is both theoretically and electrically\ngrounded in game theory, and can be viewed as a winner-shares-all two-player\ngame in which both players work as a team to achieve the best score.\nExperiments show that by working in harmony, the proposed model is able to\nclaim both the moral and log-likelihood high ground. Our work builds on a rich\nhistory of carefully argued position-papers, published as anonymous YouTube\ncomments, which prove that the optimal solution to NoN violence is more GUNs.","url_abs":"http://arxiv.org/abs/1703.02528v1","url_pdf":"http://arxiv.org/pdf/1703.02528v1.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":"stopping-gan-violence-generative","repo_url":"https://github.com/albanie/SIGBOVIK17-GUNs","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"none","reach":null}],"tasks":[],"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}