IMPLEMENTATION OF ART1 AND ART2 ARTIFICIAL NEURAL NETWORKS ON RING AND MESH ARCHITECTURES

The Artificial Neural Networks (ANNs) are being used to solve a variet y of problems in pattern recognition, robotic control, VLSI CAD and ot her areas. In most of these applications, a speedy response from the A NNs is imperative. However, ANNs comprise a large number of artificial neurons, and a massive interconnection network among them. Hence, imp lementation of these ANNs involves execution of computer-intensive ope rations. The usage of multiprocessor systems therefore becomes necessa ry. In this article, we have presented the implementation of ART1 and ART2 ANNs on ring and mesh architectures. The overall system design an d implementation aspects are presented. The performance of the algorit hm on ring, 2-dimensional mesh and n-dimensional mesh topologies is pr esented. The parallel algorithm presented for implementation of ART1 i s not specific to any particular architecture. The parallel algorithm for ARTE is more suitable for a ring architecture.