Improving collective interpretation by extended potentiality assimilation for multi-layered neural networks
The present paper aims to extend the potential learning method to overcome the problem of collective interpretation, which aims to interpret multi-layered neural networks by compressing them into the simplest ones. In the process of compression, positive, negative, and complicated weights have had u...
| Main Authors: | , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Taylor & Francis Group
2020-04-01
|
| Series: | Connection Science |
| Subjects: | |
| Online Access: | http://dx.doi.org/10.1080/09540091.2019.1674245 |
| Summary: | The present paper aims to extend the potential learning method to overcome the problem of collective interpretation, which aims to interpret multi-layered neural networks by compressing them into the simplest ones. In the process of compression, positive, negative, and complicated weights have had unfavourable effects for interpretation. To deal with the problems of collective interpretation, the potential learning is extended only to use positive weights. In addition, to obtain more appropriate weights for interpretation, the number of candidate weights for higher potentialities is first increased as much as possible. Then, from among many candidates, more appropriate weights are selected as more important ones. This extended potentiality learning is expected to produce more stable and more simple representations for easy interpretation. The extended method was applied to three datasets, namely, an artificial dataset, a real eye-tracking dataset, and a student evaluation dataset. In all cases, it was observed that the selectivity of connection weights could be increased. Correspondingly, the majority of connection weights became positive, and the collective weights were quite similar to the regression coefficients of the logistic regression analysis. Finally, for the third dataset (student evaluations), the extended method could extract more explicit input-output relations, compared with the logistic regression analysis, while improving generalisation performance. |
|---|---|
| ISSN: | 0954-0091 1360-0494 |