Training invariant support vector machines
2002
Article
ei
Practical experience has shown that in order to obtain the best possible performance, prior knowledge about invariances of a classification problem at hand ought to be incorporated into the training procedure. We describe and review all known methods for doing so in support vector machines, provide experimental results, and discuss their respective merits. One of the significant new results reported in this work is our recent achievement of the lowest reported test error on the well-known MNIST digit recognition benchmark task, with SVM training times that are also significantly faster than previous SVM methods.
Author(s): | DeCoste, D. and Schölkopf, B. |
Journal: | Machine Learning |
Volume: | 46 |
Number (issue): | 1-3 |
Pages: | 161-190 |
Year: | 2002 |
Month: | January |
Day: | 0 |
Department(s): | Empirische Inferenz |
Bibtex Type: | Article (article) |
Digital: | 0 |
DOI: | 10.1023/A:1012454411458 |
Language: | en |
Organization: | Max-Planck-Gesellschaft |
School: | Biologische Kybernetik |
Links: |
PDF
|
BibTex @article{35, title = {Training invariant support vector machines}, author = {DeCoste, D. and Sch{\"o}lkopf, B.}, journal = {Machine Learning}, volume = {46}, number = {1-3}, pages = {161-190}, organization = {Max-Planck-Gesellschaft}, school = {Biologische Kybernetik}, month = jan, year = {2002}, doi = {10.1023/A:1012454411458}, month_numeric = {1} } |