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
A Tour to Deep Learning: From the Origins to Cutting Edge Research and Open Challenges
时间:2018-05-14 20:53    点击:   所属单位:电子工程学院
讲座名称 A Tour to Deep Learning: From the Origins to Cutting Edge Research and Open Challenges
讲座时间 2018-05-16 10:10:00
讲座地点 100号楼306
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, I will provide a tour to the neural networks and deep architectures, starting from the days of the perceptron and moving to the recent trends of convolutional neural networks (CNN) and the recurrent neural networks (RNN).

I will discuss the reasons of the comeback of neural networks, after the period of the reign of the kernel machines, and present the key ideas that contributed to their current domination in the machine learning territory. The major developments that led to overcome some of their early drawbacks will be outlined and discussed, such as the ReLu and the Dropout technique.

In the sequel, I will give examples of some notable applications and discuss a couple of case studies. Finally, I am going to discuss some of their limitations and provide a short overview of the problems that are currently open and under investigation. At the end, I am going to risk some predictions for their future.

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: