首页

概率系列报告(2023/5/15 08:00-,报告人:郜传厚)

发布人:日期:2023年05月09日 11:03浏览数:

报告时间2023/5/15 开始时间:08:00

报告地址:格物楼yl23455永利307报告厅

报告题目: Programming adaptive linear neural networks through chemical reaction networks

报告摘要:In this talk, we are concerned with programming adaptive linear neural networks (ALNNs) using chemical reaction networks (CRNs) equipped with mass-action kinetics. Through individually programming the forward propagation and the backpropagation of ALNNs, and also utilizing the permeation walls technique, we construct a powerful CRN possessing the function of ALNNs, especially having the role of automatic computation. We also provide theoretical analysis and a case study to support our construction. The results will potentially impact the development of synthetic biology, molecular computer, and artificial intelligence.

报告人简介郜传厚,男,浙江大学数学科学学院教授、博士生导师。主要从事数学系统生物学、合成生物学、机器学习和优化研究,近年来已承担8项国家自然科学基金,5项省部级项目及多项企业委托项目。在国内外重要期刊/会议上发表相关学术论文70余篇,包括SIAM JournalIEEE Transactions系列会刊、AutomaticaJournal of Machine Learning ResearchMathematical Programming等国际知名期刊。现担任IEEE Transactions on Automatic ControlInternational Journal of Adaptive Control and Signal Processing等杂志编委。曾获华为 “2021年度优秀技术合作成果奖NeurIPS 2022 亮点论文。培养的博士生中,有2名毕业后直接受聘世界名校---苏黎世联邦理工学院(ETH Zürich)博士后。



上一条:创新创业教育系列报告:“互联网+”创新创业大赛(报告人:刘东海教授,报告时间:2023.5.16 15:00-16:30)

下一条:分析系列报告(2023/04/28 17:00-17:45,报告人:廖灵敏)

【关闭】 打印    收藏