Adapting the 2-class recursive deterministic perceptron neural network to m-classes
Mohamed Tajine, David A. Elizondo, Emile Fiesler, Jerzy J. Korczak · Proceedings of International Conference on Neural Networks (ICNN'97) · 2002
We introduce a generalization of the 2-class recursive deterministic perceptron (RDP). This generalization allows the perceptron to separate, in a deterministic way, into m classes. It is based on a new notion of linear separability and it falls naturally from the 2 valued RDP.