报告时间：2023/5/15 开始时间：08:00—

报告地址：格物楼数统院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 Journal和IEEE Transactions系列会刊、Automatica、Journal of Machine Learning Research、Mathematical Programming等国际知名期刊。现担任IEEE Transactions on Automatic Control、International 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。