Adaptive Resonance is primarily a theory that learning is regulated by resonance phenomena in neural circuits. Diffusion maps are a class of kernel methods on edge-weighted graphs. While either of these approaches have demonstrated success in image analysis, their combination is particularly effective. These techniques are reviewed and some example applications are given.
D. C. Wunsch et al., "Adaptive Resonance Theory and Diffusion Maps for Clustering Applications in Pattern Analysis," Donald C. Wunsch, Stephen Damelin, and Rui Xu, Jan 2014.
Model Reduction Across Disciplines (2014: Aug. 19-22, Leicester, United Kingdom)
Electrical and Computer Engineering
Center for High Performance Computing Research
Article - Conference proceedings
© 2014 Donald C. Wunsch, Stephen Damelin, and Rui Xu, All rights reserved.
01 Jan 2014