Overfitting is the most serious problem in neural network training; stopped training is the most common solution to this problem. Yet the neural network literature contains little systematic investigation of the properties of stopped training and no comparisons with statistical methods of dealing with overfitting. This paper presents the results of simulations designed to investigate these issues.
CITATION STYLE
Sarle, W. S. (1995). Stopped Training and Other Remedies for Overfitting. Proceedings of the 27th Symposium on the Interface of Computing Science and Statistics. Retrieved from citeseer.ist.psu.edu/sarle95stopped.html
Mendeley helps you to discover research relevant for your work.