A Training Scheme for Pattern Classification Using Multi-layer Feed-forward Neural Networks.
dc.contributor.author
Keeni, Kanad
en
dc.contributor.author
Nakayama, Kenji
en
dc.contributor.author
Shimodaira, Hiroshi
en
dc.date.accessioned
2006-05-26T11:50:18Z
dc.date.available
2006-05-26T11:50:18Z
dc.date.issued
1999
dc.description.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.
en
dc.format.extent
252373 bytes
en
dc.format.mimetype
application/pdf
en
dc.identifier.citation
In IEEE International Conference on Computational Intelligence and Multimedia Applications, pages 307-311, Sep 1999.
dc.identifier.uri
http://hdl.handle.net/1842/1179
dc.language.iso
en
dc.publisher
IEEE
en
dc.title
A Training Scheme for Pattern Classification Using Multi-layer Feed-forward Neural Networks.
en
dc.type
Conference Paper
en
Files
Original bundle
1 - 1 of 1
- Name:
- Keeni99.pdf
- Size:
- 246.46 KB
- Format:
- Adobe Portable Document Format
This item appears in the following Collection(s)