Transformation invariance in pattern recognition: Tangent distance and propagation

  title={Transformation invariance in pattern recognition: Tangent distance and propagation},
  author={Patrice Y. Simard and Yann LeCun and John S. Denker and Bernard Victorri},
  journal={Int. J. Imaging Systems and Technology},
In pattern recognition, statistical modeling, or regression, the amount of data is a critical factor affecting the performance. If the amount of data and computational resources are unlimited, even trivial algorithms will converge to the optimal solution. However, in the practical case, given limited data and other resources, satisfactory performance requires sophisticated methods to regularize the problem by introducing a priori knowledge. Invariance of the output with respect to certain… CONTINUE READING
Highly Cited
This paper has 44 citations. REVIEW CITATIONS


Publications citing this paper.
Showing 1-10 of 32 extracted citations

Balanced self-paced learning with feature corruption

2017 International Joint Conference on Neural Networks (IJCNN) • 2017

Bootstrap-Based Regularization for Low-Rank Matrix Estimation

Journal of Machine Learning Research • 2016
View 2 Excerpts


Publications referenced by this paper.
Showing 1-10 of 28 references

The Diabolo Classifier

Neural Computation • 1998
View 1 Excerpt

On-Line Recognition of Handwritten Symbols

IEEE Trans. Pattern Anal. Mach. Intell. • 1996
View 2 Excerpts

A model for signature verification

T. Hastie, E. Kishon, M. Clark, J. Fan
Technical Report 11214-910715-07TM, AT&T Bell Laboratories, • 1992

Local Learning Algorithms

Neural Computation • 1992
View 3 Excerpts

Revow, “Adaptive elastic models for hand-printed character recognition,” Advances in neural information processing

G. E. Hinton, C.K.I. Williams, M.D
View 2 Excerpts

Similar Papers

Loading similar papers…