- Title
- An experiment in task decomposition and ensembling for a modular artificial neural network
- Creator
- Ferguson, Brent; Ghosh, Ranadhir; Yearwood, John
- Date
- 2004
- Type
- Text; Conference paper
- Identifier
- http://researchonline.federation.edu.au/vital/access/HandleResolver/1959.17/43613
- Identifier
- vital:1345
- Identifier
-
https://doi.org/10.1007/b97304
- Abstract
- Modular neural networks have the possibility of overcoming common scalability and interference problems experienced by fully connected neural networks when applied to large databases. In this paper we trial an approach to constructing modular ANN's for a very large problem from CEDAR for the classification of handwritten characters. In our approach, we apply progressive task decomposition methods based upon clustering and regression techniques to find modules. We then test methods for combining the modules into ensembles and compare their structural characteristics and classification performance with that of an ANN having a fully connected topology. The results reveal improvements to classification rates as well as network topologies for this problem.; E1
- Publisher
- Ottawa, Canada : Springer-Verlag
- Relation
- Paper presented at Innovations in Applied Artificial Intelligence: 17th International Conference on Industrial and Engineering Applications of Artificial Intelligence and Expert Systems, Ottawa, Canada : 17th May, 2004
- Rights
- Copyright Springer
- Rights
- Open Access
- Rights
- This metadata is freely available under a CCO license
- Subject
- Neural networks; Modular neural networks; Stepwise regression; Clustering; Task decomposition
- Full Text
- Reviewed
- Hits: 6382
- Visitors: 7655
- Downloads: 1741
| Thumbnail | File | Description | Size | Format | |||
|---|---|---|---|---|---|---|---|
| View Details Download | DS1 | Accepted version | 193 KB | Adobe Acrobat PDF | View Details Download |