FUZZY ASSISTED LEARNING IN BACKPROPAGATION NEURAL NETWORKS

This paper reports on studies to overcome difficulties associated with setting the learning rates of back-propagation neural networks by usi ng fuzzy logic. Building on previous research, a fuzzy control system is designed which is capable of dynamically adjusting the individual l earning rates of both hidden and output neurons, and the momentum term within a back-propagation network. Results show that the fuzzy contro ller not only eliminates the effort of configuring a global learning r ate, but also increases the rate of convergence in comparison with a c onventional backpropagation network. Comparative studies are presented for a number of different network configurations. The paper also pres ents a brief overview of fuzzy logic and back-propagation learning, hi ghlighting how the two paradigms can enhance each other.