Research and design of distributed training algorithm for neural networks

Abstract

This paper presents a new distributed training algorithm for neural networks based on multi-agents, which is created to solve the bottleneck of memory in current prediction of protein secondary structure program, and a chip training algorithm is proposed to work in the distributed environment to evolve the global optimum by competition from a group of… (More)

Topics

5 Figures and Tables

Cite this paper

@article{Yang2005ResearchAD, title={Research and design of distributed training algorithm for neural networks}, author={Bo Yang and Yadong Wang and Xiao-hong Su}, journal={2005 International Conference on Machine Learning and Cybernetics}, year={2005}, volume={7}, pages={4044-4049 Vol. 7} }