Title :
Fault-tolerance and learning performance of the back-propagation algorithm using massively parallel implementation
Author :
Murali, Panchapagesan ; Wechsler, Harry ; Manohar, M.
Author_Institution :
Dept. of Comput. Sci., George Mason Univ., Fairfax, VA, USA
Abstract :
Mapping the backpropagation (BP) algorithm onto an SIMD (single-instruction-stream, multiple-data-stream) machine, such as the Massively Parallel Processor, is considered. It is shown that the size of the connectionist network underlying BP can be scaled up to large sizes, resulting in improved performance. Specifically, both fault tolerance and learning speed can be enhanced
Keywords :
fault tolerant computing; learning systems; multiprocessor interconnection networks; neural nets; parallel machines; Massively Parallel Processor; SIMD; back-propagation algorithm; connectionist network; fault tolerance; learning performance; massively parallel implementation; Backpropagation algorithms; Computer science; Fault tolerance; Joining processes; Mean square error methods; NASA; Neural networks; Neurons; Robustness; Transfer functions;
Conference_Titel :
Frontiers of Massively Parallel Computation, 1990. Proceedings., 3rd Symposium on the
Conference_Location :
College Park, MD
Print_ISBN :
0-8186-2053-6
DOI :
10.1109/FMPC.1990.89483
