## Neural Networks: Tricks of the Trade, Issue 1524The idea for this book dates back to the NIPS'96 workshop "Tips of the Trade" where, for the first time, a systematic attempt was made to make an assessment and evaluation of tricks for efficiently exploiting neural network techniques. Stimulated by the success of this meeting, the volume editors have prepared the present comprehensive documentation. Besides including chapters developed from the workshop contributions, they have commissioned further chapters to round out the presentation and complete the coverage of relevant subareas. This handy reference book is organized in five parts, each consisting of several coherent chapters using consistent terminology. The work starts with a general introduction and each part opens with an introduction by the volume editors. A comprehensive subject index allows easy access to individual topics. The book is a gold mine not only for professionals and researchers in the area of neural information processing, but also for newcomers to the field. |

### What people are saying - Write a review

User Review - Flag as inappropriate

h

### Contents

Introduction | 1 |

Preface | 7 |

Regularization Techniques to Improve Generalization | 51 |

Copyright | |

16 other sections not shown

### Other editions - View all

Neural Networks: Tricks of the Trade Grégoire Montavon,Geneviève Orr,Klaus-Robert Müller Limited preview - 2012 |

### Common terms and phrases

Advances in Neural algorithm applications approximation average backprop backpropagation batch Bayesian centering chapter classification clustering connectionist convergence cost function criterion cross-validation curves data set derivatives distribution early stopping eigenvalue epochs error function estimate Euclidean distance example extra tasks feed-forward Figure forecasting Gaussian gradient descent Hessian Hessian matrix hidden layer hidden units hyperparameters IEEE improve Information Processing Systems input variables learning rate linear Machine Learning main task matrix method minimal minimum network training Neural Computation Neural Information Processing neural network node noise nonlinear optimal output unit overfitting performance posterior posterior probabilities prediction risk prior probabilities probabilities problem pruning RBFN regularization parameters samples set error sigmoid SMLP speech recognition stochastic Sunspots tangent distance tangent vectors target techniques test error test set Touretzky training data training set transformation trick typically validation error validation set values variance weight decay weight update Wmin zero