LogiCook and QUESTAR: two case studies in successful technology transfer

Neural networks are ideally suited to the processing of noisy or uncertain data as they operate within a probabilistic framework. They produce probability estimates at their output and so allowance must be made for this. This is a very important consideration in the context of industrial applications and the author illustrates how this issue was addressed in the Sharp LogiCook (a neural network microwave oven) and in Oxford Medical´s QUESTAR (a neural network system for the analysis of sleep disorders)