Name
Abstract | ||
|---|---|---|
The well-known MinOver algorithm is a slight modification of the perceptron algorithm and provides the maximum-margin classifier without a bias in linearly separable two-class classification problems. DoubleMinOver as an extension of MinOver, which now includes a bias, is introduced. An O(t(-1)) convergence is shown, where t is the number of learning steps. The computational effort per step increases only linearly with the number of patterns. In its formulation with kernels, selected training patterns have to be stored. A drawback of MinOver and DoubleMinOver is that this set of patterns does not consist of support vectors only. DoubleMaxMinOver, as an extension of DoubleMinOver, overcomes this drawback by selectively forgetting all nonsupport vectors after a finite number of training steps. It is shown how this iterative procedure that is still very similar to the perceptron algorithm can be extended to classification with soft margins and be used for training least squares support vector machines (SVMs). On benchmarks, the SoftDoubleMaxMinOver algorithm achieves the same performance as standard SVM software. |
Year | DOI | Venue |
|---|---|---|
2009 | 10.1109/TNN.2009.2016717 | IEEE Transactions on Neural Networks |
Keywords | Field | DocType |
learning (artificial intelligence),least squares approximations,minimax techniques,pattern classification,perceptrons,support vector machines,DoubleMinOver algorithm,MinOver algorithm,SoftDoubleMaxMinOver algorithm,incremental learning,least squares support vector machine training,maximum-margin classifier,perceptron-like training algorithm,two-class classification problem,Incremental learning,maximum-margin classification,support vector machine (SVM) | Convergence (routing),Kernel (linear algebra),Linear separability,Pattern recognition,Computer science,Iterative method,Support vector machine,Artificial intelligence,Classifier (linguistics),Artificial neural network,Perceptron,Machine learning | Journal |
Volume | Issue | ISSN |
20 | 7 | 1941-0093 |
Citations | PageRank | References |
6 | 0.79 | 11 |
Authors | ||
3 | ||
Name | Order | Citations | PageRank |
|---|---|---|---|
| Thomas Martinetz | 1 | 1462 | 231.48 |
| Kai Labusch | 2 | 113 | 8.50 |
| Daniel Schneegass | 3 | 71 | 7.15 |