An introduction to support Vector Machines: and other kernel-based learning methods
An introduction to support Vector Machines: and other kernel-based learning methods
Pattern Recognition and Neural Networks
Pattern Recognition and Neural Networks
| Hi-index | 0.00 |
A real world problem (identifying users of body lotion from the answers given in a questionaire) is treated using a linear discriminant and a modified fault tolerant perceptron learning algorithm (pocket algorithm). As was to be expected, a fairly large error rate, which may nevertheless be acceptable for practical purposes, is obtained. A comparison with classical statistical methods (binary logistic regression) shows that the pocket algorithm does not perform as well as was previously predicted in general.