Neural Networks: Tricks of the Trade 1996

Introduction

• Genevieve B. Orr, Klaus-Robert Müller:
  Introduction. 1-5
  

Speeding Learning

• Genevieve B. Orr, Klaus-Robert Müller:
  Speeding Learning: Preface. 7-8
  
• Yann LeCun, Léon Bottou, Genevieve B. Orr, Klaus-Robert Müller:
  Effiicient BackProp. 9-50
  

Regularization Techniques to Improve Generalization

• Genevieve B. Orr, Klaus-Robert Müller:
  Regularization Techniques to Improve Generalization: Preface. 51-54
  
• Lutz Prechelt:
  Early Stopping-But When? 55-69
  
• Thorsteinn S. Rögnvaldsson:
  A Simple Trick for Estimating the Weight Decay Parameter. 71-92
  
• Tony Plate:
  Controling the Hyperparameter Search in MacKay's Bayesian Neural Network Framework. 93-112
  
• Jan Larsen, Claus Svarer, Lars Nonboe Andersen, Lars Kai Hansen:
  Adaptive Regularization in Neural Network Modeling. 113-132
  
• David Horn, Ury Naftaly, Nathan Intrator:
  Large Ensemble Averaging. 133-139
  

Improving Network Models and Algorithmic Tricks

• Genevieve B. Orr, Klaus-Robert Müller:
  Improving Network Models and Algorithmic Tricks: Preface. 141-144
  
• Gary William Flake:
  Square Unit Augmented, Radially Extended, Multilayer Perceptrons. 145-163
  
• Rich Caruana:
  A Dozen Tricks with Multitask Learning. 165-191
  
• P. Patrick van der Smagt, Gerd Hirzinger:
  Solving the Ill-Conditioning in Neural Network Learning. 193-206
  
• Nicol N. Schraudolph:
  Centering Neural Network Gradient Factors. 207-226
  
• Tony Plate:
  Avoiding Roundoff Error in Backpropagating Derivatives. 227-233
  

Representing and Incorporating Prior Knowledge in Neural Network Training

• Genevieve B. Orr, Klaus-Robert Müller:
  Representing and Incorporating Prior Knowledge in Neural Network Training: Preface. 235-238
  
• Patrice Simard, Yann LeCun, John S. Denker, Bernard Victorri:
  Transformation Invariance in Pattern Recognition-Tangent Distance and Tangent Propagation. 239-27
  
• Larry S. Yaeger, Brandyn J. Webb, Richard F. Lyon:
  Combining Neural Networks and Context-Driven Search for On-Line, Printed Handwriting Recognition in the Newton. 275-298
  
• Steve Lawrence, Ian Burns, Andrew D. Back, Ah Chung Tsoi, C. Lee Giles:
  Neural Network Classification and Prior Class Probabilities. 299-313
  
• Jürgen Fritsch, Michael Finke:
  applying Divide and Conquer to Large Scale Pattern Recognition Tasks. 315-342
  

Tricks for Time Series

• Genevieve B. Orr, Klaus-Robert Müller:
  Tricks for Time Series: Preface. 343-346
  
• John E. Moody:
  Forecasting the Economy with Neural Nets: A Survey of Challenges and Solutions. 347-371
  
• Ralph Neuneier, Hans-Georg Zimmermann:
  How to Train Neural Networks. 373-423
  

Last update Wed May 22 16:15:59 2013 CET by the DBLP Team — Data released under the ODC-BY 1.0 license — See also our legal information page