A modular approach to character recognition by neural networks

The main disadvantage of backpropagation neural networks has been the slow training rate in real-time situations where extensive training patterns and fairly extensive nets are the rule. Instead of training one huge net on the whole character set, the authors propose to implement parallel modular nets, each training on a very small character set. This approach can take full advantage of the distributed method of computing of the neural nets, will reduce the complexity of the nets, and will save a substantial amount of time otherwise required in training complex nets. The system is for the moment only applicable to a limited character set, such as the Roman alphabet