Bruce Lee random walk

Keras Blog: The future of deep learning

By Francois Chollet Mon 18 July 2017 This post is adapted from Section 3 of Chapter 9 of my book, Deep Learning with Python (Manning Publications). It is part of a series of two posts on the current limitations of deep learning, and its future. You can read the first part here: The Limitations of Deep Learning. – Given what we know of how de... Read more

Keras Blog: The limitations of deep learning

By Francois Chollet Mon 17 July 2017 This post is adapted from Section 2 of Chapter 9 of my book, Deep Learning with Python (Manning Publications). It is part of a series of two posts on the current limitations of deep learning, and its future. This post is targeted at people who already have significant experience with deep learning (e.g. pe... Read more

人物小传: Persi Diaconis

Persi Diaconis是一个传奇。他本是美国职业魔术师。为了想在赌博中不被欺骗,买了一本《An Introduction to Probability and Its Applications》,但是他没有数学基础,所以看不懂。后来他就开始在大学听数学课,并得Martin Gartner推荐,到Harvard大学读研究生,并且开始了他的研究工作。现在是Stanford的数学与统计学教授。解决了许多随机性问题(包括抛硬币,洗牌等)。如,1992与David Bayer合作证明了完美洗牌至少需要7次。再比如与澳洲学者Peter Forrester合作。 Read more

随机矩阵理论(XII): 深度学习

本文是随机矩阵理论系列的第十二篇文章,讲述了随机矩阵在深度学习中的应用,探究深度学习为什么如此有效。 深度学习 随机矩阵理论 非凸优化中的鞍点问题 几个神经网络 超限学习机(Extreme Learning Machine) 回声状态机(Echo State Machine) 研究现状 J. Silverstein, Asymptotics Applied to a Neural Network, Biol. Cybernetics, 1976. Y. L. Cun., I. I. Kanter and S. A. Solla (1991). Eigenvalues of covariance matrices: application to neu... Read more

人物小传: Freeman Dyson

Freeman Dyson是著名的数学物理学家,Princeton高等研究院教授,随机矩阵等诸多数学物理问题的初期研究者和深入者,二战期间曾参与军方研究。写过很多重要的学术论文和著名的通俗文章,如《Birds and Frogs: Selected Papers, 1990-2014》等。 Read more