|
Edinburgh Research Archive >
Centre for Speech Technology Research >
CSTR publications >
Please use this identifier to cite or link to this item:
http://hdl.handle.net/1842/1179
|
| Title: | A Training Scheme for Pattern Classification Using Multi-layer Feed-forward Neural Networks. |
| Authors: | Keeni, Kanad
Nakayama, Kenji
Shimodaira, Hiroshi |
| Issue Date: | 1999 |
| Citation: | In IEEE International Conference on Computational Intelligence and Multimedia Applications, pages 307-311, Sep 1999. |
| Publisher: | IEEE |
| Abstract: | This study highlights on the subject of weight
initialization in multi-layer feed-forward networks.
Training data is analyzed and the notion of criti-
cal point is introduced for determining the initial
weights for the input to hidden layer synaptic con-
nections. The proposed method has been applied to
artificial data. The experimental results show that
the proposed method takes almost 1/2 of the train-
ing time required for standard back propagation. |
| URI: | http://hdl.handle.net/1842/1179 |
| Appears in Collections: | CSTR publications
|
Items in ERA are protected by copyright, with all rights reserved, unless otherwise indicated.
|
