Framework for distributed artificial neural system simulation
Roger Barga, Ronald B. Melton · OSTI OAI (U.S. Department of Energy Office of Scientific and Technical Information) · 1989
In this paper, we describe a distributed artificial neural system (ANS) simulation environment for research on large-scale ANS networks. The ANSkit, as the environment is called, allows local graphics workstations to utilize ANS simulation engines implemented on remote supercomputers and to interactively display the results of the simulation. The ANSkit design uses extensive data compression and standard network protocols to permit its use over wide area, as well as local area networks. The ANSkit demonstrates an easily used, simulation visualization capability for ANS in a heterogeneous, distributed computing environment. Further, ANSkit demonstrates how remote supercomputing resources can provide a cost-effective tool for ANS research. 8 refs., 3 figs.