A Simulator to Parallelise Large Biologically-Inspired Artificial Neural Networks
This paper presents parallel simulator for artificial neural networks development. This simulator uses the intrinsic neuron parallelism of the connectionists models to map the neural networks onto shared memory MIMD general purpose parallel computers. Due to this method, the simulator is more especially dedicated to large biologically inspired neural networks.
KeywordsNeural Network Artificial Neural Network Shared Memory Parallel Machine Parallel Simulator
Unable to display preview. Download preview PDF.
- Y. Boniface, F. Alexandre, and S. Vialle, “A bridge between two paradigms for parallelism: Neural networks and general purpose MIMD computers.” in IJGNN, 1999.Google Scholar
- Y. Boniface, F. Alexandre, and S. Vialle, “A library to implement neural networks on MIMD machines” in EuroPar’99, 1999.Google Scholar
- T. Reski, Mapping and Parallel, Distributed Simulation of Neural Networks on Message Passing Multiprocessors. PhD thesis, Universität Paderborn, 1999.Google Scholar
- N. Sundararajan and P. Saratchandran, Parallel architectures for artificial neural network, Paradigms and Implementation. IEEE computer society, 1998.Google Scholar
- H. Paugam-Moisy, “Multiprocessor simulation of neural networks.” in The Handbook of Brain Theory and Neural Network., pp. 605–608, The MIT Press., 1995.Google Scholar
- L. Bougrain and Y. Boniface, “Détermination de l’architecture de modèles neuromimétiques par implémentation parallèle” in Journées Scientifiques du CCH, 2000.Google Scholar