Clusters in the input-output problem space represent "patches" of data, which can be represented as rules. Neurons in competitive learning neural networks learn to represent centers of clusters. A weight vector wj may be viewed as a geometrical center of a cluster of data.
- Limitations of Competitive Learning, neural-network,pdfs, lecture-notes, downloads
- Neural Networks Can Memorize and Approximate Fuzzy Rules, download classroom notes
- Learning Vector Quantization Algorithms for Supervised Learning in Neural Networks free notes pdf
- Hopfield networks, supervised learning in Neural Networks free pdf
- Hebbian learning rule in Neural Networks free pdf