LARGE NEURAL NETWORK: OBJECT MODELING AND PARALLEL SIMULATION
Carlos J. Garcı́a-Orellana, Francisco J. Lopez-Aligue, Horacio M. González–Velasco, Miguel Macías Macías, M. Isabel Acevedo-Sotoca · International Journal of Artificial Intelligence Tools · 2001
We propose an object oriented model for the simulation of large neural networks using the OMT technique. This modeling has been implemented on a client-server parallel simulator (called NeuSim-NNLIB), the server being a "beowulf" cluster, getting up to 18 MCPS with a cluster of 6 Pentium processors. We also present an estimation for simulator performance and optimal processors number.