题目：A New Algorithm for Machine Learning and Artificial Intelligence

报告人：夏志宏教授 （美国西北大学 / 大湾区大学）  

摘 要： We propose a novel machine learning algorithm inspired by complex analysis. Our algorithm has a better mathematical formulation and can approximate universal functions much more efficiently. The algorithm can be implemented in two self-learning neural networks: The CauchyNet and the XNet. The CauchyNet is very efficient for low-dimensional problems such as extrapolation, imputation, numerical solutions of PDEs and ODEs. The XNet, on the other hand, works for large dimensional problems such as image and voice recognition, transformer and large language models.  We implemented our algorithm for many scenarios, showing that it is very efficient and acurate. It is much better than than many popular PINN (Physically Inspired Neural; Network) models in various scientific computations; It outperforms KAN (Kolmogorov Arnold Network);  For a set of medical image we tested, it can increase accuracy from 88% to 98%. Our algorithm is currently being tested on large language models. Small scale testing shows great promise.  

报告人简介：夏志宏，大湾区大学（筹）讲座教授，美国西北大学数学系潘克讲席教授。主要研究兴趣为动力系统、太阳系动力学、人工智能算法。主要成就包括解决百年悬而未决的庞勒维猜想，和黎健一起发现几亿年曾有太阳系外大行星在木星与土星之间飞过。夏志宏曾获多项国际重大学术奖励，包括美国国家青年研究者奖、Sloan Research Fellowship、首届Blumenthal Award for Advancement of Pure Mathematics、Monroe Martin应用数学奖，国际数学家大会（ICM）报告人（1998）。夏志宏先后任教于哈佛大学（1988，助理教授），佐治亚理工学院（1990，副教授），美国西北大学（1994，教授；2000，潘克讲席教授）；1999年受聘为北京大学数学学院第一批长江计划特聘教授；2015年受聘为南方科技大学数学系创系系主任。夏志宏2015年参与建立未来科学大奖，是大奖科学委员会创始成员；2020起为《知识分子》总编辑之一。  

报告时间：2024年11月29日（周五）下午15:00-16:00  

报告地点：教二楼113  

联系人：孙善忠