A parallel formulation of back-propagation learning on distributed memory multiprocessors Academic Article uri icon

abstract

  • This paper presents a mapping scheme for parallel pipelined execution of the Back-propagation Learning Algorithm on distributed memory multiprocessors. The proposed implementation exhibits inter-layer or pipelined parallelism, unique to the multilayer neural networks. Simple algorithms have been presented, which allow the data transfer involved in both recall and learning phases of the back-propagation algorithm to be carried out with a small communication overhead. The effectiveness of the mapping scheme has been illustrated, by estimating the speedup of the proposed implementation on an array of T-805 transputers.

published proceedings

  • Parallel Computing

author list (cited authors)

  • Mahapatra, S., Mahapatra, R. N., & Chatterji, B. N.

citation count

  • 9

complete list of authors

  • Mahapatra, S||Mahapatra, RN||Chatterji, BN

publication date

  • February 1997