每周论坛之四（总第219期）：林盈（中山大学），2019年9月23日下午

每周论坛之四  （总第219期）

报告人：林盈 副教授

报告人单位：中山大学心理学系

题目：运用人工神经网络预测真实神经网络的研究

From Artificial Neural Network to Its Natural Counterpart: A Preliminary Study

时间：2019年 9 月23 日 （周一，14:20-16:00）

地点：中山大学东校园心理学系（南学院楼C座）305

报告简介：

    It has been widely recognized that functional connectivity between brain regions is based on and constrained by the structural topology. However, detailed relationships between structural and functional aspects of the human brain remain largely unknow. In this study, we used the artificial neural network approach to build an edgewise prediction model, which predicted the function connectivity between two brain regions from the topological attributes of the related structural connectivity. The contributions of the topological attributes to the prediction result were then analyzed to help gain insight into the question of how structural topology can affect the formation of functional connectivity. Further, the prediction model was extended to a cross-data scenario to testify its generalization ability.

报告人简介：

    林盈，中山大学心理学系副教授，主要研究方向为计算智能及其在复杂网络分析和智慧教育中的应用。目前已在IEEE Transactions on Cybernetics, Neuroimage等国际学术期刊和会议上发表论文30余篇，引用次数达1000余次。主持国家自然科学基金项目2项。