Name
Abstract | ||
|---|---|---|
Connectionist networks are interesting computational models that have been proved to be useful for a range of applications. Knowledge in connectionist networks is encoded in distributed internal weights. Learning algorithms based on numerical optimisation techniques can adapt these weights for a specific task (e.g., pattern classification). One of the major criticisms against the connectionist approach, however, is that knowledge generated by neural networks is not explicitly represented in the form of rules suitable for verification or interpretation, i.e., they are often regarded as black boxes. The authors discuss the ability of information exchange between connectionist and symbolic representations in a novel hybrid knowledge-based connectionist network, called HKBCN. With the newly developed hybrid approach, domain knowledge can be encoded into the network, revised over time, and decoded into symbolic forms |
Year | DOI | Venue |
|---|---|---|
1997 | 10.1109/APSEC.1997.640167 | APSEC |
Keywords | Field | DocType |
optimisation,computational models,knowledge based systems,symbolic representation,hybrid approach,novel hybrid knowledge-based connectionist,black box,black boxes,symbol manipulation,hybrid knowledge-based connectionist network,learning systems,interpretation,verification,hybrid intelligent system,knowledge revising,numerical optimisation techniques,knowledge representation,domain knowledge encoding,explanation,connectionist representation,learning algorithms,interesting computational model,rules,information exchange,distributed internal weights,knowledge verification,connectionist approach,domain knowledge,neural nets,symbolic form,connectionist network,hkbcn,neural networks,artificial intelligence,computer networks,application software,software engineering,computer model,telephony,neural network,computational modeling,knowledge base | DUAL (cognitive architecture),Knowledge representation and reasoning,Neuro-fuzzy,Domain knowledge,Computer science,Knowledge-based systems,Hybrid intelligent system,Artificial intelligence,Artificial neural network,Connectionism,Machine learning | Conference |
ISBN | Citations | PageRank |
0-8186-8271-X | 0 | 0.34 |
References | Authors | |
7 | 2 | |
Name | Order | Citations | PageRank |
|---|---|---|---|
| Xinyu Wu | 1 | 0 | 0.34 |
| John G. Hughes | 2 | 326 | 59.84 |