Self-organizing maps
Comparing support vector machines with Gaussian kernels to radialbasis function classifiers
IEEE Transactions on Signal Processing
| Hi-index | 0.00 |
This paper proposes the use of interpolating vectorsfor robust pattern recognition. Labeled reference vectors in a multi-dimensional feature space are first produced by a kind of competitive learning. We then assume a situation where interpolating vectors are densely placed along lines connecting all pairs of reference vectors of the same label. From these interpolating vectors, we choose the one that has the largest similarity to the test vector. Its label shows the result of pattern recognition. We applied this method to the neocognitronfor handwritten digit recognition, and reduced the error rate from 1.48% to 1.00% for a blind test set of 5000 digits.