Manifold Construction Using the Multilayer Perceptron

Authors:
Wei-Chen Cheng;Cheng-Yuan Liou
Affiliations:
Department of Computer Science and Information Engineering, National Taiwan University, Republic of China, Supported by National Science Council,;Department of Computer Science and Information Engineering, National Taiwan University, Republic of China, Supported by National Science Council,
Venue:
ICANN '08 Proceedings of the 18th international conference on Artificial Neural Networks, Part I
Year:
2008

Citing 6
Cited 0

Learning internal representations by error propagation

Parallel distributed processing: explorations in the microstructure of cognition, vol. 1
Improved multidimensional scaling analysis using neural networks with distance-error backpropagation

Neural Computation
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

Quantified Score

Hi-index	0.00

Visualization

Abstract

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.