NON-MONOTONIC REASONING WITH CONNECTIONIST NETWORKS USING COARSE-CODED REPRESENTATIONS
This paper, describes a connectionist fault-tolerant non-monotonic reasoning system, which uses coarse-coded distributed representations. Distributed representations are known to give the advantages of fault tolerance, generalization and graceful degradation of performance under noise conditions. A semantic network is designed, using a novel approach, with connectionist networks using coarse-coded representations to perform non-monotonic reasoning. The system performs non-monotonic reasoning using the property of inheritance. The system also supports the feature of cancellation of inheritance, whereby more specific information precedence over default information associated with the nodes higher in the hierarchy. System has exhibited good generalization ability on unseen test inputs. Systems performance with regard to its ability to exhibit fault tolerance under noise conditions is also studied. The system offers very good results of fault tolerance under noise conditions.
Connectionist coarse-coded fault-tolerance non-monotonic reasoning semantic-network
SRIRAM .G.SANJEEVI PUSHPAK BHATTACHARYYA
Department of Computer Science & Engg., National Institute of Technology, Warangal 506004, India Department of Computer Science & Engg., Indian Institute of Technology, Bombay, India
国际会议
2006 International Conference on Machine Learning and Cybernetics(IEEE第五届机器学习与控制论坛)
大连
英文
3048-3052
2006-08-13（万方平台首次上网日期，不代表论文的发表时间）