Locally Regularized Learning Systems

After joining AT&T Bell Laboratories in 1991, I worked with Vladimir Vapnik on the links between learning technique and the widely used regularization techniques. I applied local regularization methods to optical character recognition and bettered all previous systems on our USPS benchmark with a 3.3% error rate. Alas the algorithm was quite slow. Three months later, Patrice Simard took the record, achieving 2.5% error with Tangent Distances. I do not remember which was the slowest algorithm.


Léon Bottou and Vladimir N. Vapnik: Local Learning Algorithms, Neural Computation, 4(6):888-900, 1992.


Vladimir N. Vapnik and Léon Bottou: Local Algorithms for Pattern Recognition and Dependencies Estimation, Neural Computation, 5(6):893-909, 1993.


Léon Bottou, Corinna Cortes, John S. Denker, Harris Drucker, Isabelle Guyon, Lawrence D. Jackel, Yann Le Cun, Urs A. Muller, Eduard Säckinger, Patrice Simard and Vladimir Vapnik: Comparison of classifier methods: a case study in handwritten digit recognition, Proceedings of the 12th IAPR International Conference on Pattern Recognition, Conference B: Computer Vision & Image Processing., 2:77-82, IEEE, Jerusalem, October 1994.


research/local.txt · Last modified: 2007/08/17 11:50 by leonb
Driven by DokuWiki Recent changes RSS feed Valid CSS Valid XHTML 1.0