Proceedings of the Korean Operations and Management Science Society Conference (한국경영과학회:학술대회논문집)
- 1995.09a
- /
- Pages.325-333
- /
- 1995
Efficient weight initialization method in multi-layer perceptrons
- Han, Jaemin (College of Business Administration Korea University) ;
- Sung, Shijoong (College of Business Administration Korea University) ;
- Hyun, Changho (College of Business Administration Korea University)
- Published : 1995.09.01
Abstract
Back-propagation is the most widely used algorithm for supervised learning in multi-layer feed-forward networks. However, back-propagation is very slow in convergence. In this paper, a new weight initialization method, called rough map initialization, in multi-layer perceptrons is proposed. To overcome the long convergence time, possibly due to the random initialization of the weights of the existing multi-layer perceptrons, the rough map initialization method initialize weights by utilizing relationship of input-output features with singular value decomposition technique. The results of this initialization procedure are compared to random initialization procedure in encoder problems and xor problems.
Keywords