Description |
1 online resource |
Series |
Lecture notes in computer science ; 7700 |
|
LNCS sublibrary. SL 1, Theoretical computer science and general issues |
|
Lecture notes in computer science ; 7700.
|
|
LNCS sublibrary. SL 1, Theoretical computer science and general issues.
|
Contents |
Introduction / Klaus-Robert Müller -- Speeding Learning / Klaus-Robert Müller -- Efficient BackProp / Yann A. LeCun, Léon Bottou, Genevieve B. Orr and Klaus-Robert Müller -- Regularization Techniques to Improve Generalization / Klaus-Robert Müller -- Early Stopping -- But When? / Lutz Prechelt -- A Simple Trick for Estimating the Weight Decay Parameter / Thorsteinn S. Rögnvaldsson -- Controlling the Hyperparameter Search in MacKay's Bayesian Neural Network Framework / Tony Plate -- Adaptive Regularization in Neural Network Modeling / Jan Larsen, Claus Svarer, Lars Nonboe Andersen and Lars Kai Hansen -- Large Ensemble Averaging / David Horn, Ury Naftaly and Nathan Intrator -- Improving Network Models and Algorithmic Tricks / Klaus-Robert Müller -- Square Unit Augmented, Radially Extended, Multilayer Perceptrons / Gary William Flake -- A Dozen Tricks with Multitask Learning / Rich Caruana -- Solving the Ill-Conditioning in Neural Network Learning / Patrick van der Smagt and Gerd Hirzinger -- Centering Neural Network Gradient Factors / Nicol N. Schraudolph -- Avoiding Roundoff Error in Backpropagating Derivatives / Tony Plate |
|
Representing and Incorporating Prior Knowledge in Neural Network Training / Klaus-Robert Müller -- Transformation Invariance in Pattern Recognition -- Tangent Distance and Tangent Propagation / Patrice Y. Simard, Yann A. LeCun, John S. Denker and Bernard Victorri -- Combining Neural Networks and Context-Driven Search for On-line, Printed Handwriting Recognition in the Newton / Larry S. Yaeger, Brandyn J. Webb and Richard F. Lyon -- Neural Network Classification and Prior Class Probabilities / Steve Lawrence, Ian Burns, Andrew Back, Ah Chung Tsoi and C. Lee Giles -- Applying Divide and Conquer to Large Scale Pattern Recognition Tasks / Jürgen Fritsch and Michael Finke -- Tricks for Time Series / Klaus-Robert Müller -- Forecasting the Economy with Neural Nets: A Survey of Challenges and Solutions / John Moody -- How to Train Neural Networks / Ralph Neuneier and Hans Georg Zimmermann -- Big Learning and Deep Neural Networks / Grégoire Montavon and Klaus-Robert Müller -- Stochastic Gradient Descent Tricks / Léon Bottou -- Practical Recommendations for Gradient-Based Training of Deep Architectures / Yoshua Bengio -- Training Deep and Recurrent Networks with Hessian-Free Optimization / James Martens and Ilya Sutskever |
|
Implementing Neural Networks Efficiently / Ronan Collobert, Koray Kavukcuoglu and Clément Farabet -- Better Representations: Invariant, Disentangled and Reusable / Grégoire Montavon and Klaus-Robert Müller -- Learning Feature Representations with K-Means / Adam Coates and Andrew Y. Ng -- Deep Big Multilayer Perceptrons for Digit Recognition / Dan Claudiu Cireşan, Ueli Meier, Luca Maria Gambardella and Jürgen Schmidhuber -- A Practical Guide to Training Restricted Boltzmann Machines / Geoffrey E. Hinton -- Deep Boltzmann Machines and the Centering Trick / Grégoire Montavon and Klaus-Robert Müller -- Deep Learning via Semi-supervised Embedding / Jason Weston, Frédéric Ratle, Hossein Mobahi and Ronan Collobert -- Identifying Dynamical Systems for Forecasting and Control / Grégoire Montavon and Klaus-Robert Müller -- A Practical Guide to Applying Echo State Networks / Mantas Lukoševičius -- Forecasting with Recurrent Neural Networks: 12 Tricks / Hans-Georg Zimmermann, Christoph Tietz and Ralph Grothmann -- Solving Partially Observable Reinforcement Learning Problems with Recurrent Neural Networks / Siegmund Duell, Steffen Udluft and Volkmar Sterzing -- 10 Steps and Some Tricks to Set up Neural Reinforcement Controllers / Martin Riedmiller |
Summary |
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 |
Analysis |
computerwetenschappen |
|
computer sciences |
|
informatiesystemen |
|
information systems |
|
internet |
|
patroonherkenning |
|
pattern recognition |
|
algoritmen |
|
algorithms |
|
computeranalyse |
|
computer analysis |
|
kunstmatige intelligentie |
|
artificial intelligence |
|
computational science |
|
Information and Communication Technology (General) |
|
Informatie- en communicatietechnologie (algemeen) |
Bibliography |
Includes bibliographical references and indexes |
Notes |
English |
|
Print version record |
Subject |
Neural networks (Computer science)
|
|
Neural Networks, Computer
|
|
Informatique.
|
|
Neural networks (Computer science)
|
Form |
Electronic book
|
Author |
Montavon, Grégoire
|
|
Orr, Geneviève B
|
|
Müller, Klaus-Robert.
|
ISBN |
9783642352898 |
|
3642352898 |
|
364235288X |
|
9783642352881 |
|