A Novel, Fast-Learning Neutral Network

Abstract

As we published in the last few years[1-7], when the given input-output training vector pairs satisfy a PLI(positive-liner-independency) condition, the training of a hard-limited neural network to learn this mapping can be achieved non-iteratively with very short training time and very robust recognition when any untrained patterns are tested in the recognition mode. The key feature in this novel pattern recognition system is the use of slack constants in sloving the connection matrix when the PLI condition is satisfied. Generally there are infinitely many ways of selecting the slack constants for meeting the training-recognition goal, but there is noly one way to select them if an optimal robustness is sought in the recognition of the untrained patterns. This particulay way of selecting the slack constants carries some special physical properties of the system -- the automatic feature extraction in the learning mode and the automatic featrre competition in the recognition mode. Physical signigicance as well as mathematical analysis of thes novel properites are to be explained in detail in this article. Real-time experiments are to be presented in an unedited movie. It is seen that in the system, the training of 4 hand-written characters is close to real time(<0.1 sec.) and the recognition of the untrained hand-written characters is >905 accurate.