加入收藏夹
联系我们
关于本站
个人主页
西电导航
西安电子科技大学
    当前位置:首页>>学术讲座
fMRI Data Analysis: A Dictionary Learning and Tensor Algebra Framework
时间:2018-05-14 08:29    点击:   所属单位:电子工程学院
讲座名称 fMRI Data Analysis: A Dictionary Learning and Tensor Algebra Framework
讲座时间 2018-05-15 09:00:00
讲座地点 新科技楼1702
讲座人 Sergios Theodoridis
讲座人介绍

Sergios Theodoridis is currently Professor of Signal Processing and Machine Learning in the Department of Informatics and Telecommunications of the University of Athens. His research interests lie in the areas of Adaptive Algorithms, Distributed and Sparsity-Aware Learning, Machine Learning and Pattern Recognition, Signal Processing for Audio Processing and Retrieval. He is the co-editor of the book "Efficient Algorithms for Signal Processing and System Identification", Prentice Hall 1993, the co-author of the best selling book "Pattern Recognition", Academic Press, 4th ed. 2008, the co-author of the book "Introduction to Pattern Recognition: A MATLAB Approach", Academic Press, 2009, the co-author of the book "Introduction to Pattern Recognition: A MATLAB Approach", Academic Press, 2010, the author of the book "Machine Learning: A Bayesian and Optimization approach" Academic Press, 2015, and the co-author of three books in Greek, two of them for the Greek Open University.

讲座内容

In this talk, we will discuss novel results concerning the task of fMRI data analysis

The focus will be on latent variables and blind matrix factorization, one of the hottest areas in learning, since compact representation of the available data is of paramount importance. Our emphasis is on dictionary leaning (DL) techniques. Signals are represented in terms of learnable, from the data, “bases” vectors (dictionaries). Moreover, these dictionaries can comprise a large number of possible vectors, and the notion of sparsity is mobilized to select the “good” ones. In our talk, a modification of the standard DL approach is proposed, where one can impose a-priori knowledge, in the context of fMRI, in certain parts of the dictionaries to be learned. New techniques and optimization algorithms are discussed and related experimental results are presented.

Finally, some hints on using multiway arrays (tensors), in the context of fMRI data analysis, are discussed. Multiway arrays are becoming more and more popular, since they can grasp better the underlying structure (correlations) that is hidden in the data and can help the user in extracting and learning related information. In our research, a new unfolding of the brain images is proposed that builds around a tensor representation of the brain image.

转载请注明出处:西安电子科技大学学术信息网
如果您有学术信息或学术动态,欢迎投稿。我们将在第一时间确认并收录,投稿邮箱: meeting@xidian.edu.cn
Copyright © 2011-2018 西安电子科技大学 
开发维护:电子工程学院网络信息中心  管理员:meeting@xidian.edu.cn 站长统计: