{"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/one-shot-generation-of-near-optimal-topology","title":"One-Shot Generation of Near-Optimal Topology through Theory-Driven Machine Learning","arxiv_id":"1807.10787","date":"2018-07-27","proceeding":null,"authors":["Ruijin Cang","Hope Yao","Yi Ren"],"abstract":"We introduce a theory-driven mechanism for learning a neural network model\nthat performs generative topology design in one shot given a problem setting,\ncircumventing the conventional iterative process that computational design\ntasks usually entail. The proposed mechanism can lead to machines that quickly\nresponse to new design requirements based on its knowledge accumulated through\npast experiences of design generation. Achieving such a mechanism through\nsupervised learning would require an impractically large amount of\nproblem-solution pairs for training, due to the known limitation of deep neural\nnetworks in knowledge generalization. To this end, we introduce an interaction\nbetween a student (the neural network) and a teacher (the optimality conditions\nunderlying topology optimization): The student learns from existing data and is\ntested on unseen problems. Deviation of the student's solutions from the\noptimality conditions is quantified, and used for choosing new data points to\nlearn from. We call this learning mechanism \"theory-driven\", as it explicitly\nuses domain-specific theories to guide the learning, thus distinguishing itself\nfrom purely data-driven supervised learning. We show through a compliance\nminimization problem that the proposed learning mechanism leads to topology\ngeneration with near-optimal structural compliance, much improved from standard\nsupervised learning under the same computational budget.","url_abs":"http://arxiv.org/abs/1807.10787v3","url_pdf":"http://arxiv.org/pdf/1807.10787v3.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":"one-shot-generation-of-near-optimal-topology","repo_url":"https://github.com/DesignInformaticsLab/Theory_Driven_TO","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"none","reach":null}],"tasks":[{"task_slug":"machine-learning","task_name":"BIG-bench Machine Learning"}],"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}