Title :
A novel method to stop neural network training
Author :
Iyer, Mahesh S. ; Rhinehart, R. Russell
Author_Institution :
Dresser-Rand Control Syst., Houston, TX, USA
Abstract :
A novel approach of stopping neural network training has been evaluated. The approach improves data utilization, provides a statistical rationale to stop training, and seems to present a robust method for automating the stopping of neural network training
Keywords :
learning (artificial intelligence); neural nets; stability; statistical analysis; data utilization; neural network training stopping; robust method; statistical rationale; Chemical engineering; Control systems; Costs; Humans; Monitoring; Neural networks; Productivity; Robustness; Steady-state; Testing;
Conference_Titel :
American Control Conference, 2000. Proceedings of the 2000
Conference_Location :
Chicago, IL
Print_ISBN :
0-7803-5519-9
DOI :
10.1109/ACC.2000.876636
