Computing Reviews
Today's Issue Hot Topics Search Browse Recommended My Account Log In
Review Help
Search
Computational methods for deep learning: theoretic, practice and applications
Yan W., Springer International Publishing, Cham, Switzerland, 2021. 211 pp. Type: Book (978-3-030610-80-7)
Date Reviewed: Apr 23 2021

Computational methods for deep learning is written for the typical second-year graduate student at a US university, working in this area for his/her PhD-level dissertation research on the application of various manifestations of deep networks. This is not an introductory textbook to this subject, but a manual of sorts that is meant for those who already know the fundamentals of artificial neural networks (ANNs) and many of its variants, including convolutional neural networks (CNNs), recurrent neural networks (RNNs), and the basics of supervised learning using back-propagation-based minimization strategies [1]. However, it also contains a wealth of recent information on the various implementations and applications of deep networks.

This book is divided into eight short chapters. Chapter 1 contains a very good historical introduction to the evolution of the deep network. Chapter 2 gives a detailed and useful account of the various platforms available for implementing deep networks on various platforms. A quick overview of CNNs and RNNs and a short review of the mathematical tools, including concepts from function and metric spaces, are listed. Short overviews of autoencoders and reinforcement learning are contained in chapters 4 and 5, respectively. Special topics like manifold learning, deep Boltzmann machines, and ensemble learning are covered in the last three chapters.

Each chapter contains a good set of exercise problems dealing largely with implementation, as well as ample references to current literature; the index is quite useful to find your way through the book. While it may not be easy to learn the basics from scratch, this book is a good resource with rather extensive pointers to the current literature on this important and growing area.

Reviewer:  S. Lakshmivarahan Review #: CR147247 (2108-0201)
Bookmark and Share
  Reviewer Selected
Featured Reviewer
 
 
Learning (I.2.6 )
 
Would you recommend this review?
yes
no
Other reviews under "Learning": Date
Learning in parallel networks: simulating learning in a probabilistic system
Hinton G. (ed) BYTE 10(4): 265-273, 1985. Type: Article
Nov 1 1985
Macro-operators: a weak method for learning
Korf R. Artificial Intelligence 26(1): 35-77, 1985. Type: Article
Feb 1 1986
Inferring (mal) rules from pupils’ protocols
Sleeman D.  Progress in artificial intelligence (, Orsay, France,391985. Type: Proceedings
Dec 1 1985
more...

E-Mail This Printer-Friendly
Send Your Comments
Contact Us
Reproduction in whole or in part without permission is prohibited.   Copyright 1999-2024 ThinkLoud®
Terms of Use
| Privacy Policy