威尼斯人

报告地点：逸夫楼 423

腾讯会议：271-778-598 （//meeting.tencent.com/dm/IQ0TXlnNKMwk）

报告摘要：Backpropagation (BP) algorithm is one of the most basic learning algorithms in deep learning. Although BP has been widely used, it still suffers from the problem of easily falling into the local minima due to its gradient dynamics. Inspired by the fact that the learning of real brains may exploit chaotic dynamics, we propose the chaotic backpropagation (CBP) algorithm by integrating the intrinsic chaos of real neurons into BP. By validating on multiple datasets (e.g. cifar10), we show that, for multilayer perception (MLP), CBP has significantly better abilities than those of BP and its variants in terms of optimization and generalization from both computational and theoretical viewpoints. Actually, CBP can be regarded as a general form of BP with global searching ability inspired by the chaotic learning process in the brain. Therefore, CBP not only has the potential of complementing or replacing BP in deep learning practice, but also provides a new way for understanding the learning process of the real brain.

报告人简介：陈洛南教授，1984年获华中科技大学电气工程学士学位，1988年获日本东北大学系统科学硕士学位，1991年获日本东北大学系统科学博士学位。1997年起任日本大阪产业大学副教授,2000年起任美国加州大学洛杉矶分校(UCLA)访问教授,2002年起任日本大阪产业大学教授,2009年4月起任日本东京大学教授(兼),2010年4月至今任中科院系统生物学重点实验室执行主任，研究员。现任中国生物化学与分子生物学会分子系统生物学专业分会主任委员，IEEE-SMC系统生物学委员会主席，中国运筹学会计算系统生物学分会名誉理事长。主要从事计算系统生物学、大数据分析和人工智能的研究工作。近年来，在系统生物学和复杂网络等研究领域发表了350余篇期刊论文及10余部编著书籍(Citation > 20000; H-index > 70; Elsevier高被引)。

邀请人： 颜洁