A Parallel Incremental Learning Algorithm for Neural Networks with Fault Tolerance
Jacques M. Bahi (LIFC, University of Franche-Comté, Belfort, France)Sylvain Contassot-Vivier (LORIA, University Henri Poincaré, Nancy, France)
Marc Sauget (LIFC, University of Franche-Comté, Belfort, France)
Aurélien Vasseur (Femto-St, University of Franche-Comté, Montbéliard, France)
Abstract:
This paper presents a parallel and fault tolerant version of
an incremental learning algorithm for feed-forward neural
networks used as function approximators. It has been shown
in previous works that our incremental algorithm builds
networks of reduced size while providing high quality
approximations for real data sets. However, for very large
sets, the use of our learning process on a single machine
may be quite long and even sometimes impossible, due to
memory limitations. The parallel algorithm presented in
this paper is usable in any parallel system, and in
particular, with large dynamical systems such as clusters
and grids in which faults may occur. Finally, the quality
and performances (without and with faults) of that algorithm
are experimentally evaluated.
Keywords:
Parallel and Distributed Computing, Cluster Computing, Grid Computing (middleware, algorithms, performance evaluation, ...), Computing in Healthcare and Biosciences
