Joydeep Ghosh Arindam C Nag

This paper presents a technique for enhancing an RBFN when provided with additional information in the form of new features, without retraining or resorting to the original fea-tures. The proposed technique improves the learning speed as well as network performance as compared to a network that is trained from scratch. We also present a method of reusing knowledge em-bedded in an RBFN for initializing another RBFN to be trained on a related problem. Both methods have several real-life applications.