日日干日日摸-日日干天天操-日日干天天草-日日干天天插-精品一区二区三区在线观看-精品一区二区三区在线观看l

437bwin必贏國際官網(集團)有限公司-SouG百科

學術報告:Evolutionary Learning: From Theory to Practice

發布時間:2024-11-04     瀏覽量:

報告題目:Evolutionary Learning: From Theory to Practice

報告時間:202411414:30

報告地點:437bwin必贏國際官網E202

報告人:錢超

報告人單位:南京大學

報告人簡介:錢超,南京大學人工智能學院教授博導。長期從事人工智能中演化學習基礎理論研究,以第一/通訊作者在人工智能國際一流期刊和會議上發表50余篇論文,出版專著Evolutionary LearningACM GECCO’11最佳理論論文獎,受邀擔任IEEE計算智能學會“演化算法理論分析”工作組主席,獲CCF-IEEE CS青年科學家獎2023)。部分成果成功應用于華為工廠排產、無線網絡優化、芯片寄存器尋優等任務,獲2次華為難題揭榜火花獎落地華為產品線;應用于自然科學基礎問題(如土壤微生物源碳預測),成果以共同一作發表于美國國家科學院院刊PNAS。擔任人工智能/演化計算權威國際期刊Artificial IntelligenceEvolutionary ComputationIEEE Trans. Evolutionary Computation等編委在國際人工智能聯合大會IJCAI’22Early Career Spotlight報告,并將擔任第22屆亞太人工智能國際會議PRICAI25程序委員會主席。獲國家優秀青年科學基金(2020,并主持新一代人工智能國家科技重大專項(青年科學家)指導本科生獲國自然本科生項目,執教《啟發式搜索與演化算法》被研究生選為我心目中的好課程,獲南京大學青年五四獎章、師德先進青年教師獎

報告摘要Machine learning tasks often involve complex optimization, like black-box and multi-objective optimization, which may make conventional optimization algorithms fail. Evolutionary algorithms, inspired by Darwin’s theory of evolution, have yielded encouraging outcomes. However, due to their heuristic nature, most outcomes to date have been empirical and lack theoretical support. In this talk, I will introduce our efforts towards building the theoretical foundation of evolutionary learning and developing better algorithms inspired by theories. Finally, I will introduce some successful applications in industry (e.g., electronic design automation) and science (e.g., studying the origin and evolution of life).