Automated design of neural networks for symbolic signal processing

A procedure is described for translating high-level knowledge about an application into a neural network architecture that incorporates that knowledge in its synaptic interconnections. The program´s design philosophy stresses separation of neural design from network function, a uniform syntax for neurons, inputs, and outputs, and flexibility in modularizing the resulting network. The trainability of neural networks allows the application knowledge to be further fine-tuned for a specific data space. It is shown how the translation rules can allow for the selective training of subnetworks, and an example of a signal recognition algorithm to which this technique can be applied is given