|
| << previous | next >> |
Journal description
All volumes of the corresponding journal
All issues of the corresponding volume
All articles of the corresponding issues
Details for article 42 of 76 found articles
| Title: |
Improving feature extraction performance of greedy network-growing algorithm by inverse euclidean distance |
| Author: |
Kamimura, Ryotaro |
| Appeared in: |
Connection science |
| Paging: | Volume 16 (2004) nr. 2 pages 129-138 |
| Year: |
2004-06 |
| Contents: |
We propose here a new computational method for the information-theoretic method, called the greedy network-growing algorithm, to facilitate a process of information acquisition. We have so far used the sigmoidal activation function for competitive unit outputs. The method can effectively suppress many competitive units by generating strongly negative connections. However, because methods with the sigmoidal activation function are not very sensitive to input patterns, we have observed that in some cases final representations obtained by the method do not necessarily faithfully describe input patterns. To remedy this shortcoming, we employ the inverse of distance between input patterns and connection weights for competitive unit outputs. As the distance becomes smaller, competitive units are more strongly activated. Thus, winning units tend to represent input patterns more faithfully than in the previous method with the sigmoidal activation function. We applied the new method to artificial data analysis and animal classification. Experimental results confirmed that more information can be acquired and more explicit features can be extracted by our new method. |
| Publisher: |
Taylor & Francis |
| Source file: |
Elektronische Wetenschappelijke Tijdschriften |
Details for article 42 of 76 found articles
| << previous | next >> |