1st International Workshop on Combinations of Intelligent Methods and Applications | |
Improving the Accuracy of Neuro-Symbolic Rules withCase-Based Reasoning | |
Jim Prentzas ; Ioannis Hatzilygeroudis ; Othon Michail | |
Others : http://CEUR-WS.org/Vol-375/paper9.pdf PID : 46814 |
|
来源: CEUR | |
【 摘 要 】
In this paper, we present an improved approach integrating rules, neural networks and cases, compared to aprevious one. The main approach integrates neurules and cases.Neurules are a kind of integrated rules that combine a symbolic (production rules) and a connectionist (adaline unit)representation. Each neurule is represented as an adaline unit. The main characteristics of neurules are that they improve theperformance of symbolic rules and, in contrast to other hybridneuro-symbolic approaches, retain the modularity of production rules and their naturalness in a large degree. In the improved approach, various types of indices are assigned to cases according to different roles they play in neurule-based reasoning, instead of one. Thus, an enhanced knowledgerepresentation scheme is derived resulting in accuracyimprovement. Experimental results demonstrate its effectiveness.
【 预 览 】
Files | Size | Format | View |
---|---|---|---|
Improving the Accuracy of Neuro-Symbolic Rules withCase-Based Reasoning | 291KB | download |