Artificial Neural Networks Hardware Implementation

Abstract

In the last decade the ANNs have shown massive computing capabilities. They are being used more and more in many fields because of their robustness and plasticity of architecture. To take full advantage of the ANNs, researchers have been working hard to find a better way to implement these networks in software or hardware. The ANN implementation has shown some difficulties. Thus a study to select the best implementation has been introduced. Each available hardware technology has its own advantages, and drawbacks. There have been many approaches to classify the neural hardware. In this thesis, it is listed some of the classification approaches used, and then the types of neural hardware used according to HEEMSKERK classification approach. To conclude some examples on neural hardware was given.