Deep Learning Architectures - Calin, Ovidiu; - Prospero Internet Bookshop
Basket (0)
Wishlist (0)
Your personal newsletter
__

Deep Learning Architectures: A Mathematical Approach
 
Product details:
ISBN13:9783030367237
ISBN10:3030367231
Binding:Paperback
No. of pages:760 pages
Size:254x178 mm
Weight:1480 g
Language:English
Illustrations: 172 Illustrations, black & white; 35 Illustrations, color
889
Category:

Deep Learning Architectures

A Mathematical Approach
 
Edition number: 1st ed. 2020
Publisher: Springer
Date of Publication:
Number of Volumes: 1 pieces, Book
 
Normal price:
Publisher's listprice:
EUR 69.54
Estimated price in HUF:
29 644 HUF (28 233 HUF + 5% VAT)
Why estimated?
 
Your price:
23 716 (22 586 HUF + 5% VAT )
discount is: 20% (approx 5 929 HUF off)
Discount is valid until: 31 December 2024
The discount is only available for 'Alert of Favourite Topics' newsletter recipients.
Click here to subscribe.
 
Availability:
Estimated delivery time: In stock at the publisher, but not at Prospero's office. Delivery time approx. 3-5 weeks.
Not in stock at Prospero.
Can't you provide more accurate information?
 
Add to basket
  Piece(s)

 
Short 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.



 



 


Long 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.

 

 




?This book is useful to students who have already had an introductory course in machine learning and are further interested to deepen their understanding of the machine learning material from the mathematical point of view.? (T. C. Mohan, zbMATH 1441.68001, 2020)

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.