Title :
Distributed fuzzy learning using the MULTISOFT machine
Author_Institution :
Dipartimento di Fisica, Messina Univ., Italy
fDate :
5/1/2001 12:00:00 AM
Abstract :
Describes PARGEFREX, a distributed approach to genetic-neuro-fuzzy learning which has been implemented using the MULTISOFT machine, a low-cost form of personal computers built at the University of Messina. The performance of the serial version is hugely enhanced with the simple parallelization scheme described in the paper. Once a learning dataset is fixed, there is a very high super linear speedup in the average time needed to reach a prefixed learning error, i.e., if the number of personal computers increases by n times, the mean learning time becomes less than 1/n times
Keywords :
MIMO systems; fuzzy logic; genetic algorithms; learning (artificial intelligence); message passing; parallel machines; MULTISOFT machine; PARGEFREX; distributed fuzzy learning; genetic-neuro-fuzzy learning; learning dataset; mean learning time; parallelization scheme; prefixed learning error; Computer networks; Fuzzy logic; Hardware; MIMO; Machine learning; Microcomputers; Modeling; Multiprocessor interconnection networks; Neural networks; Supervised learning;
Journal_Title :
Neural Networks, IEEE Transactions on
