Pattern Recognition Using Neural Networks: Theory and Algorithms for Engineers and Scientists

This work covers linear pattern recognition and its non-linear extension via neural networks from an algorithmic approach. The text explores multiple layered preceptrons and describes network types such as functional link, radial basis function, learning vector quantanization and self-organizing.
This work covers traditional linear pattern recognition and its non-linear extension via neural networks from an algorithmic approach. The text explores multiple layered preceptrons and describes network types such as functional link, radial basis function, learning vector quantanization and self-organizing. It also discusses recent clustering methods. This text is suitable for an advanced undergraduate course in pattern recognition or neural networks, and should also be useful as a reference and a resource.