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

报 告 人：郜传厚教授（浙江大学）

报告时间：2023年5月15日  08:00-12:00

报告地点：格物楼数统院307报告厅

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。