Name
Title | ||
|---|---|---|
Direct Rule Extraction From A Mlp Network That Performs Whole Life Assurance Risk Assessment |
Abstract | ||
|---|---|---|
Using a new method published by the first author this paper shows how to directly induce a rule from any training input case for a Multilayer Perceptron network (MLP) that performs a Whole Life Assurance risk assessment task. For selected input training cases the paper finds the hidden layer feature detector neurons which leads to the discovery of the significant or key, inputs that the network uses to classify, applicants for Whole Life Assurance into Standard and Non-Standard risk. The ranking of the significant inputs and negated significant inputs enables the knowledge learned by the network during training to be extracted in the form of induced rules which show that the network learns sensibly and very effectively when compared with the training data set. This study demonstrates the potential value of the knowledge extraction method for MLP network validation and case-by-case interpretation, both during network learning and network use. |
Year | Venue | Keywords |
|---|---|---|
1998 | ICONIP'98: THE FIFTH INTERNATIONAL CONFERENCE ON NEURAL INFORMATION PROCESSING JOINTLY WITH JNNS'98: THE 1998 ANNUAL CONFERENCE OF THE JAPANESE NEURAL NETWORK SOCIETY - PROCEEDINGS, VOLS 1-3 | risk assessment |
Field | DocType | Citations |
Data mining,Computer science,Risk assessment,Artificial intelligence,Artificial neural network,Machine learning | Conference | 0 |
PageRank | References | Authors |
0.34 | 1 | 3 |
Name | Order | Citations | PageRank |
|---|---|---|---|
| Marylin L. Vaughn | 1 | 9 | 3.13 |
| Everest T. Ong | 2 | 127 | 10.50 |
| Steven J. Cavill | 3 | 9 | 2.79 |