English Polski
On-line access


0.00 PLN
Bookshelf (0) 
Your bookshelf is empty
Deep Learning Architectures: A Mathematical Approach

Deep Learning Architectures: A Mathematical Approach

Publisher Springer, Berlin
Pages 760
Version paperback
Language English
ISBN 9783030367237
Categories Mathematical theory of computation
$112.90 (with VAT)
501.90 PLN / €107.61 / £93.41
Delivery to United States

check shipping prices
Would you like to be informed when the book becomes available? Please provide your e-mail address and you will be the first to know:
Add to bookshelf

Book description

This book describes how neural networks operate from the mathematical point of view. As a result, neural networks can be interpreted both as function universal approximators and information processors. The book bridges the gap between ideas and concepts of neural networks, which are used nowadays at an intuitive level, and the precise modern mathematical language, presenting the best practices of the former and enjoying the robustness and elegance of the latter.

This book can be used in a graduate course in deep learning, with the first few parts being accessible to senior undergraduates.  In addition, the book will be of wide interest to machine learning researchers who are interested in a theoretical understanding of the subject.



Deep Learning Architectures: A Mathematical Approach

Table of contents

Introductory Problems.- Activation Functions.- Cost Functions.- Finding Minima Algorithms.- Abstract Neurons.- Neural Networks.- Approximation Theorems.- Learning with One-dimensional Inputs.- Universal Approximators.- Exact Learning.- Information Representation.- Information Capacity Assessment.- Output Manifolds.- Neuromanifolds.- Pooling.- Convolutional Networks.- Recurrent Neural Networks.- Classification.- Generative Models.- Stochastic Networks.- Hints and Solutions. 

We also recommend books

Strony www Białystok Warszawa
801 777 223