The remarkable practical success of deep learning has revealed some major surprises from
a theoretical perspective. In particular, simple gradient methods easily find near-optimal …

In this paper we investigate the family of functions representable by deep neural networks
(DNN) with rectified linear units (ReLU). We give an algorithm to train a ReLU DNN with one …

This important work describes recent theoretical advances in the study of artificial neural
networks. It explores probabilistic models of supervised learning problems, and addresses …

The decade prior to publication has seen an explosive growth in com-tational speed and
memory and a rapid enrichment in our understa-ing of arti? cial neural networks. These two …

Delineating the tremendous growth in this area, the Handbook of Approximation Algorithms
and Metaheuristics covers fundamental, theoretical topics as well as advanced, practical …

From the Publisher: How does it differ from first edition__ __ Includes new material on:*
support vector machines (SVM's),* fat shattering dimensions* applications to neural network …

Understanding the fundamental mechanism behind the success of deep neural networks is
one of the key challenges in the modern machine learning literature. Despite numerous …

We address the computational complexity of learning in the agnostic framework. For a
variety of common concept classes we prove that, unless P= NP, there is no polynomial time …

Several recently proposed architectures of neural networks such as ResNeXt, Inception,
Xception, SqueezeNet and Wide ResNet are based on the designing idea of having multiple …

Understanding the fundamental principles behind the success of deep neural networks is
one of the most important open questions in the current literature. To this end, we study the …