The Margin Perceptron with Unlearning
Abstract
We introduce into the classical Perceptron algorithm with margin a mechanism of unlearning which in the course of the regular update allows for a reduction of possible contributions from �very well classified� patterns to the weight vector. The resulting incremental classification algorithm, called Margin Perceptron with Unlearning (MPU), provably converges in a finite number of updates to any desirable chosen before running approximation of either the maximal margin or the optimal 1-norm soft margin solution. Moreover, an experimental comparative evaluation involving representative linear Support Vector Machines reveals that the MPU algorithm is very competitive.
Cite
Text
Panagiotakopoulos and Tsampouka. "The Margin Perceptron with Unlearning." International Conference on Machine Learning, 2010.Markdown
[Panagiotakopoulos and Tsampouka. "The Margin Perceptron with Unlearning." International Conference on Machine Learning, 2010.](https://mlanthology.org/icml/2010/panagiotakopoulos2010icml-margin/)BibTeX
@inproceedings{panagiotakopoulos2010icml-margin,
title = {{The Margin Perceptron with Unlearning}},
author = {Panagiotakopoulos, Constantinos and Tsampouka, Petroula},
booktitle = {International Conference on Machine Learning},
year = {2010},
pages = {855-862},
url = {https://mlanthology.org/icml/2010/panagiotakopoulos2010icml-margin/}
}