Region of influence (ROI) networks. Model and implementation
Two different approaches in constructing Neural Network (NN) classifiers are discussed — discriminant-based networks and Region of Influence networks. A general model for ROI networks is presented, and the different functionalities of this structure are discussed: classification, vector quantization and associative memory.
Also, an architecture for this model's implementation is presented, and the hardware realization of each layer is reviewed in detail.
Unable to display preview. Download preview PDF.
- 1.Reilly D.L., Cooper L.N., Elbaum C. A neural model for category learning. Biological Cybernetics, 45, 35–41 1982Google Scholar
- 2.Alpaydin A.I. Neural models of incremental supervised and unsupervised learning. PhD Thesis Lausanne EPFL 1990Google Scholar
- 3.Castillo F. Digital VLSI Architectures for Neural Networks. PhD Thesis Universidad Politécnica de Catalunya 1992Google Scholar