Can General Purpose Micro-processors Simulate Neural Networks in Real-Time?

By their universal character, general purpose micro-processors may be used to simulate artificial neural networks. However, until now, they were not capable to perform these simulations in real-time. On the other hand, the computational power of these processors has tremendously increased recently. Thus, one may wonder whether up-to-date general purpose micro processors can simulate neural networks in real-time. To answer this question, we need to evaluate the performance of these architectures for the simulation of neural networks. To realize this evaluation we have developed an original methodology which can predict the simulation time of a neural network on an electronic architecture. This prediction is based on an analytic of the architecture performances.