↓ Skip to main content

Neural Networks: Tricks of the Trade

Overview of attention for book
Cover of 'Neural Networks: Tricks of the Trade'

Table of Contents

  1. Altmetric Badge
    Book Overview
  2. Altmetric Badge
    Chapter 1 Introduction
  3. Altmetric Badge
    Chapter 2 Speeding Learning
  4. Altmetric Badge
    Chapter 3 Efficient BackProp
  5. Altmetric Badge
    Chapter 4 Regularization Techniques to Improve Generalization
  6. Altmetric Badge
    Chapter 5 Early Stopping — But When?
  7. Altmetric Badge
    Chapter 6 A Simple Trick for Estimating the Weight Decay Parameter
  8. Altmetric Badge
    Chapter 7 Controlling the Hyperparameter Search in MacKay’s Bayesian Neural Network Framework
  9. Altmetric Badge
    Chapter 8 Adaptive Regularization in Neural Network Modeling
  10. Altmetric Badge
    Chapter 9 Large Ensemble Averaging
  11. Altmetric Badge
    Chapter 10 Improving Network Models and Algorithmic Tricks
  12. Altmetric Badge
    Chapter 11 Square Unit Augmented, Radially Extended, Multilayer Perceptrons
  13. Altmetric Badge
    Chapter 12 A Dozen Tricks with Multitask Learning
  14. Altmetric Badge
    Chapter 13 Solving the Ill-Conditioning in Neural Network Learning
  15. Altmetric Badge
    Chapter 14 Centering Neural Network Gradient Factors
  16. Altmetric Badge
    Chapter 15 Avoiding Roundoff Error in Backpropagating Derivatives
  17. Altmetric Badge
    Chapter 16 Representing and Incorporating Prior Knowledge in Neural Network Training
  18. Altmetric Badge
    Chapter 17 Transformation Invariance in Pattern Recognition – Tangent Distance and Tangent Propagation
  19. Altmetric Badge
    Chapter 18 Combining Neural Networks and Context-Driven Search for On-line, Printed Handwriting Recognition in the Newton
  20. Altmetric Badge
    Chapter 19 Neural Network Classification and Prior Class Probabilities
  21. Altmetric Badge
    Chapter 20 Applying Divide and Conquer to Large Scale Pattern Recognition Tasks
  22. Altmetric Badge
    Chapter 21 Tricks for Time Series
  23. Altmetric Badge
    Chapter 22 Forecasting the Economy with Neural Nets: A Survey of Challenges and Solutions
  24. Altmetric Badge
    Chapter 23 How to Train Neural Networks
  25. Altmetric Badge
    Chapter 24 Big Learning and Deep Neural Networks
  26. Altmetric Badge
    Chapter 25 Stochastic Gradient Descent Tricks
  27. Altmetric Badge
    Chapter 26 Practical Recommendations for Gradient-Based Training of Deep Architectures
  28. Altmetric Badge
    Chapter 27 Training Deep and Recurrent Networks with Hessian-Free Optimization
  29. Altmetric Badge
    Chapter 28 Implementing Neural Networks Efficiently
  30. Altmetric Badge
    Chapter 29 Better Representations: Invariant, Disentangled and Reusable
  31. Altmetric Badge
    Chapter 30 Learning Feature Representations with K-Means
  32. Altmetric Badge
    Chapter 31 Deep Big Multilayer Perceptrons for Digit Recognition
  33. Altmetric Badge
    Chapter 32 A Practical Guide to Training Restricted Boltzmann Machines
  34. Altmetric Badge
    Chapter 33 Learning Feature Hierarchies with Centered Deep Boltzmann Machines
  35. Altmetric Badge
    Chapter 34 Deep Learning via Semi-supervised Embedding
  36. Altmetric Badge
    Chapter 35 Identifying Dynamical Systems for Forecasting and Control
  37. Altmetric Badge
    Chapter 36 A Practical Guide to Applying Echo State Networks
  38. Altmetric Badge
    Chapter 37 Forecasting with Recurrent Neural Networks: 12 Tricks
  39. Altmetric Badge
    Chapter 38 Solving Partially Observable Reinforcement Learning Problems with Recurrent Neural Networks
  40. Altmetric Badge
    Chapter 39 10 Steps and Some Tricks to Set up Neural Reinforcement Controllers
Attention for Chapter 17: Transformation Invariance in Pattern Recognition – Tangent Distance and Tangent Propagation
Altmetric Badge

About this Attention Score

  • Average Attention Score compared to outputs of the same age
  • Above-average Attention Score compared to outputs of the same age and source (62nd percentile)

Mentioned by

2 patents


382 Dimensions

Readers on

271 Mendeley
1 CiteULike
You are seeing a free-to-access but limited selection of the activity Altmetric has collected about this research output. Click here to find out more.
Chapter title
Transformation Invariance in Pattern Recognition – Tangent Distance and Tangent Propagation
Chapter number 17
Book title
Neural Networks: Tricks of the Trade
Published in
Lecture notes in computer science, January 2012
DOI 10.1007/978-3-642-35289-8_17
Book ISBNs
978-3-64-235288-1, 978-3-64-235289-8

Patrice Y. Simard, Yann A. LeCun, John S. Denker, Bernard Victorri, Simard, Patrice Y., LeCun, Yann A., Denker, John S., Victorri, Bernard


Grégoire Montavon, Geneviève B. Orr, Klaus-Robert Müller

Mendeley readers

Mendeley readers

The data shown below were compiled from readership statistics for 271 Mendeley readers of this research output. Click here to see the associated Mendeley record.

Geographical breakdown

Country Count As %
United States 7 3%
United Kingdom 4 1%
Spain 3 1%
Germany 2 <1%
Japan 2 <1%
Canada 2 <1%
Australia 1 <1%
India 1 <1%
Hong Kong 1 <1%
Other 4 1%
Unknown 244 90%

Demographic breakdown

Readers by professional status Count As %
Student > Ph. D. Student 80 30%
Student > Master 47 17%
Researcher 41 15%
Student > Bachelor 22 8%
Other 14 5%
Other 39 14%
Unknown 28 10%
Readers by discipline Count As %
Computer Science 150 55%
Engineering 48 18%
Mathematics 8 3%
Psychology 5 2%
Business, Management and Accounting 4 1%
Other 23 8%
Unknown 33 12%
Attention Score in Context

Attention Score in Context

This research output has an Altmetric Attention Score of 3. This is our high-level measure of the quality and quantity of online attention that it has received. This Attention Score, as well as the ranking and number of research outputs shown below, was calculated when the research output was last mentioned on 11 October 2022.
All research outputs
of 23,505,669 outputs
Outputs from Lecture notes in computer science
of 8,137 outputs
Outputs of similar age
of 247,458 outputs
Outputs of similar age from Lecture notes in computer science
of 489 outputs
Altmetric has tracked 23,505,669 research outputs across all sources so far. This one is in the 44th percentile – i.e., 44% of other outputs scored the same or lower than it.
So far Altmetric has tracked 8,137 research outputs from this source. They typically receive a little more attention than average, with a mean Attention Score of 5.1. This one has gotten more attention than average, scoring higher than 54% of its peers.
Older research outputs will score higher simply because they've had more time to accumulate mentions. To account for age we can compare this Altmetric Attention Score to the 247,458 tracked outputs that were published within six weeks on either side of this one in any source. This one is in the 41st percentile – i.e., 41% of its contemporaries scored the same or lower than it.
We're also able to compare this research output to 489 others from the same source and published within six weeks on either side of this one. This one has gotten more attention than average, scoring higher than 62% of its contemporaries.