Deep learning has been widely applied and brought breakthroughs in speech recognition, computer vision, and many other domains. The involved deep neural network architectures and computational issues have been well studied in machine learning. But there lacks a theoretical foundation for understanding the modelling, approximation or generalization ability of deep learning models with network architectures. Here we are interested in deep convolutional neural networks (CNNs) with convolutional structures. The convolutional architecture gives essential differences between the deep CNNs and fully-connected deep neural networks, and the classical theory for fully-connected networks developed around 30 years ago does not apply. This talk describes a mathematical theory of deep CNNs associated with the rectified linear unit (ReLU) activation function.



 



In particular, we give the first proof for the universality of deep CNNs, meaning that a deep CNN can be used to approximate any continuous function to an arbitrary accuracy when the depth of the neural network is large enough. We also give explicit rates of approximation, and show that the approximation ability of deep CNNs is at least as good as that of fully-connected multi-layer neural networks for general functions, and is better for radial functions. Our quantitative estimate, given tightly in terms of the number of free parameters to be computed, verifies the efficiency of deep CNNs in dealing with big data.

11月18日
3pm - 4:20pm
地点
https://hkust.zoom.us/j/98248767613 (Passcode: math6380p)
讲者/表演者
Prof. Ding-Xuan ZHOU
City University of Hong Kong
主办单位
Department of Mathematics
联系方法
付款详情
对象
Alumni, Faculty and staff, PG students, UG students
语言
英语
其他活动
4月26日
研讨会, 演讲, 讲座
IAS / School of Science Joint Lecture - Molecular Basis of Wnt Biogenesis, Secretion and Ligand Specific Signaling
Abstract Wnt signaling is essential to regulate embryonic development and adult tissue homeostasis. Aberrant Wnt signaling is associated with cancers. The ER-resident membrane-bound O-acyltransfera...
4月18日
研讨会, 演讲, 讲座
IAS / School of Science Joint Lecture - Understanding the Roles of Transposable Elements in the Human Genome
Abstract Transposable elements (TEs) have expanded the binding repertoire of many transcription factors and, through this process, have been co-opted in different transcriptional networks. In this ...