Abstract
Introductory accounts of artificial neural networks often rely for motivation on analogies with models of information processing in biological networks. One limitation of such an approach is that it offers little guidance on how to find optimal algorithms, or how to verify the correct performance of neural network systems. A central goal of this paper is to draw attention to a quite different viewpoint in which neural networks are seen as algorithms for statistical pattern recognition based on a principled, i.e. theoretically well-founded, framework. We illustrate the concept of a principled viewpoint by considering a specific issue concerned with the interpretation of the outputs of a trained network. Finally, we discuss the relevance of such an approach to the issue of the validation and verification of neural network systems.
| Original language | English |
|---|---|
| Title of host publication | Neural Networks - Producing Dependable Systems: Conference Proceedings, 2 November 1995 |
| Place of Publication | Surrey |
| Publisher | ERA technology |
| Pages | 3.1.1-3.1.9 |
| ISBN (Print) | 0700805931 |
| Publication status | Published - Mar 1996 |
| Event | Proceedings of the ERA Technology Conference: Neural Networks -- Producing Dependable Systems - Duration: 1 Mar 1996 → 1 Mar 1996 |
Conference
| Conference | Proceedings of the ERA Technology Conference: Neural Networks -- Producing Dependable Systems |
|---|---|
| Period | 1/03/96 → 1/03/96 |
Keywords
- artificial neural networks
- information processing
- biological networks
- optimal algorithms
- correct performance
- neural network systems
- statistical pattern recognition
- principled viewpoint
- trained network
- validation
- verification