Editors:
- The second edition of the book "reloads" the first edition with more tricks
- Provides a timely snapshot of tricks, theory and algorithms that are of use
Part of the book series: Lecture Notes in Computer Science (LNCS, volume 7700)
Part of the book sub series: Theoretical Computer Science and General Issues (LNTCS)
Buy it now
Buying options
Tax calculation will be finalised at checkout
Other ways to access
This is a preview of subscription content, log in via an institution to check for access.
Table of contents (39 chapters)
-
Front Matter
-
Introduction
-
Speeding Learning
-
Regularization Techniques to Improve Generalization
-
Improving Network Models and Algorithmic Tricks
-
Representing and Incorporating Prior Knowledge in Neural Network Training
About this book
The twenty last years have been marked by an increase in available data and computing power. In parallel to this trend, the focus of neural network research and the practice of training neural networks has undergone a number of important changes, for example, use of deep learning machines.
The second edition of the book augments the first edition with more tricks, which have resulted from 14 years of theory and experimentation by some of the world's most prominent neural network researchers. These tricks can make a substantial difference (in terms of speed, ease of implementation, and accuracy) when it comes to putting algorithms to work on real problems.
Editors and Affiliations
-
Dept. of Computer Science, Technische Universität Berlin, Berlin, Germany
Grégoire Montavon, Klaus-Robert Müller
-
Dept. of computer Science, Willamette University, Salem, USA
Geneviève B. Orr
Bibliographic Information
Book Title: Neural Networks: Tricks of the Trade
Editors: Grégoire Montavon, Geneviève B. Orr, Klaus-Robert Müller
Series Title: Lecture Notes in Computer Science
DOI: https://doi.org/10.1007/978-3-642-35289-8
Publisher: Springer Berlin, Heidelberg
eBook Packages: Computer Science, Computer Science (R0)
Copyright Information: Springer-Verlag Berlin Heidelberg 2012
Softcover ISBN: 978-3-642-35288-1Published: 06 November 2012
eBook ISBN: 978-3-642-35289-8Published: 14 November 2012
Series ISSN: 0302-9743
Series E-ISSN: 1611-3349
Edition Number: 2
Number of Pages: XII, 769
Number of Illustrations: 223 b/w illustrations
Topics: Computation by Abstract Devices, Artificial Intelligence, Algorithm Analysis and Problem Complexity, Pattern Recognition, Complexity, Information Systems Applications (incl. Internet)