【学术视频】统计物理与神经计算国际研讨会 | 北京大学吴思教授

更多精彩视频登陆网站

www.koushare.com

图 | 吴思

题   目：Push-pull feedback implements rough-to-fine information retrieval报告人：吴思单   位：北京大学时   间：2019-10-05地   点：中山大学

扫码观看精彩报告视频

报告摘要

Experimental data has revealed that in addition to feedforward connections, there exist abundant feedback connections in a hierarchical neural pathway. Although the importance of feedback in neural information processing has been widely recognized in the field, the detailed mechanism of how it works remains largely unknown. Here, we investigate the role of feedback in hierarchical memory retrieval. Specifically, we consider a multi-layer network which stores hierarchical memory patterns, and each layer of the network behaves as an associative memory of the corresponding hierarchy. We find that to achieve good retrieval performance, the feedback needs to be dynamical: at the early phase, the feedback is positive (push), which suppresses inter-class noises between memory patterns; at the late phase, the feedback is negative (pull), which suppresses intra-class noises between memory patterns. Overall, memory retrieval in the network progresses from rough to fine. Our model agrees with the push-pull phenomenon observed in neural data and sheds light on our understanding of the role of feedback in neural information processing.

个人简介

Dr. Si Wu is Professor at School of Electronics Engineering & Computer Science, Principle Investigator at IDG/McGovern Institute for Brain Research, and Principle Investigator at PKU-Tsinghua Center for Life Science in Peking University. He was originally trained as a theoretical physicist and received his BSc, MSc, and PhD degrees all from Beijing Normal University. His research interests have turned to Artificial Intelligence and Computational Neuroscience since graduation. He worked as Postdocs at Hong Kong University of Science & Technology, Limburg University of Belgium, and Riken Brain Science Institute of Japan, and as Lecturer/Senior Lecturers at Sheffield University and Sussex University of UK. He came back to China in 2008, and worked as PI at Institute of Neuroscience in Chinese Academy of Sciences and Professor in Beijing Normal University. His research interests focus on Computational Neuroscience and Brain-inspired Computing. He has published more than 100 papers, including top journals in neuroscience, such as Neuron, Nature Neuroscience, PNAS, J. Neurosci., and top conferences in AI, such as NIPS. He is now Co-editor-in-chief of Frontiers in Computational Neuroscience.

会议简介

2019年10月4日-6日，统计物理与神经计算国际研讨会由中山大学物理学院主办，这是在该校举办的第一届物理，机器学习与计算神经科学交叉的国际会议，会议邀请了这一领域近年来作出杰出贡献的国内外专家参与讨论，并围绕神经网络的计算建模，理论研究，生物机制的最新进展展开。

—— ——往期精彩回顾—— ——●【学术视频】统计物理与神经计算国际研讨会 | Adriano Barra of Università del Salento: Guerra's interpolation in machine learning & neural networks●【学术视频】统计物理与神经计算国际研讨会 | Taro Toyoizumi of RIKEN CBS:Exploring the learning principle in the brain●【学术视频】统计物理与神经计算国际研讨会 | 英国阿斯顿大学David Saad教授：Function-Space Entropy in Deep-Learning Networks●【学术视频】统计物理与神经计算国际研讨会 | Alexis Dubreuil: Disentangling the roles of dimensionality and cell classes in neural computation●【学术视频】机器学习-计算化学Workshop | 复旦大学刘智攀教授：Global optimization based Neural Network Potential and Reaction Prediction Artificial Intelligence●【学术视频】第一届量子算法与软件国际研讨会 | 中科院计算技术研究所孙晓明研究员：Optimal Space-Depth Trade-Off of CNOT Circuits●【学术视频】第13届全国分子束外延学术会议 | 清华大学郝智彪教授：氮化物纳米线量子点分子束外延与特性研究●【学术视频】纪念黄昆先生诞辰一百周年暨半导体学科发展研讨会 | 中科院上海微系统与信息技术研究所王浩敏研究员：基于石墨烯纳米带的异质结构筑与逻辑器件探索●【学术视频】第五届全国统计物理与复杂系统学术会议 | 北京工业大学刘鑫副教授：流体纽结复杂系综级联退化过程的拓扑学研究

END

扫描二维码，关注微信公众号

戳这里，观看精彩视频哟！