Learning internal representations by error propagation
Parallel distributed processing: explorations in the microstructure of cognition, vol. 1
Conformal self-organization for continuity on a feature map
Neural Networks
Resolving Hidden Representations
Neural Information Processing
Manifold Construction by Local Neighborhood Preservation
Neural Information Processing
Smooth seamless surface construction based on conformal self-organizing map
ICONIP'06 Proceedings of the 13 international conference on Neural Information Processing - Volume Part I
Hi-index | 0.00 |
We present a training method which adjusts the weights of the MLP (Multilayer Perceptron) to preserve the distance invariance in a low dimensional space. We apply visualization techniques to display the detailed representations of the trained neurons.