Main problems and issues in neural networks application

Summary form only given. Some of the specific problems that have been faced by the author in using neural networks in different application areas are outlined. They concern justifying the use of neural nets: the apparent ad hoc nature of the method; the lack of sufficient training data; the lack of an acceptable validation procedure; the need to relate network weights to physical parameters; the widespread disparities in training times (learning times) while solving apparently simple problems; the need for progress in the hardware implementation area; the need to develop adaptive control systems based on biological prototypes, and the need for a synthesis procedure in neural network research