Quantitative analysis of kernel properties in Kohonen's self-organizing map algorithm: Gaussian and difference of Gaussians neighborhoods.
Mimi LiljeholmAndy LinPiotr OzdzynskiJackson BeattyPublished in: Neurocomputing (2002)
Keyphrases
- self organizing maps
- quantitative analysis
- k means
- feature maps
- input data
- neural network
- learning algorithm
- neural gas
- competitive learning
- energy function
- centroid neural network
- qualitative analysis
- computer vision
- particle swarm optimization algorithm
- segmentation algorithm
- multiscale
- feature extraction
- topology preserving
- color image segmentation
- learning vector quantization
- machine learning