报告题目：Towards the next generation of AI: visual computation with neural spikes
报 告 人：刘健教授 英国莱斯特大学
报告时间：2020年6月4日 16:00-17:00
报告地点：腾讯会议ID：292 189 248
或点击链接直接加入会议：
https://meeting.tencent.com/s/WOYmez8MFYyi
校内联系人：孙维鹏 sunwp@jlu.edu.cn
报告摘要：
Neuromorphic computing has been suggested as the next generation of computational strategy. In neuroscience, neural coding is for understanding how the brain processes stimulus from the environment, moreover, it is also a cornerstone for designing algorithms of brain-machine inference. Here, I will show some of the recent progress that has been achieved in data-driven visual computation models that use neural spikes to analyze natural scenes. I hypothesize that we need a hyper-circuit view of neural network computing framework, in which specific computations are utilized by different network motifs inspired by techniques of probabilistic graph models and deep learning. As a proof of concept, the revealed mechanisms and proposed algorithms can provide new insights into neuromorphic computing for next-generation of general-purpose AI.
报告人简介：
刘健博士，吉林大学数学学士，北京大学力学硕士，美国加州大学洛杉矶分校数学博士，先后为法国国家科学院和哥廷根大学博士后研究员。曾为奥地利格拉兹理工大学理论计算机研究所助理教授，参与欧盟旗舰研究项目“人脑计划”。现为英国莱斯特大学系统神经科学中心长聘助理教授。研究领域为计算神经科学与类脑智能，神经网络学习与记忆，视觉系统编码。近年来在Nature communications, eLife, Journal of neuroscience, PLoS computational biology, IEEE Transactions on Neural Networks and Learning Systems, IEEE Transactions on cybernetics等顶级期刊发表多篇论文。研究资助方包括欧盟研究委员会，英国皇家学会牛顿高级学者基金，中国之江实验室。
