Acceleration of back propagation through initial weight pre-training with delta rule Conference Paper uri icon

abstract

  • A new training strategy for Back Propagation (BP) neural networks, named Delta Pre-Training (DPT), is proposed. The core of the new training strategy is based on pre-training the initial weights for BP networks using the Delta rule, instead of using random values. After pre-training, the normal BP training procedure is carried out to complete network training. With the DPT, the convergence rate for training BP networks can be significantly improved. With regards to on-chip learning in VLSI implementations, only a little additional circuitry is required for the pre-training phase with the DPT. Simulation results using the proposed training method show its superiority over previous methods.

published proceedings

  • 1993 IEEE International Conference on Neural Networks

author list (cited authors)

  • Li, G., Alnuweiri, H., Wu, Y., & Li, H.

complete list of authors

  • Li, G||Alnuweiri, H||Wu, Y||Li, H

publication date

  • January 1993