Symbolic-neural rule based reasoning and explanation

作者：

Highlights：

• Neurules, a type of neuro-symbolic rules, retain naturalness and modularity.

• Reasoning and explanation mechanisms for neurules are presented.

• Two types of inference processes: a connectionism-oriented and symbolism-oriented.

• Symbolism-oriented inference more efficient than connectionism-oriented.

• More efficient and natural explanation compared to connectionist expert systems.

摘要

•Neurules, a type of neuro-symbolic rules, retain naturalness and modularity.•Reasoning and explanation mechanisms for neurules are presented.•Two types of inference processes: a connectionism-oriented and symbolism-oriented.•Symbolism-oriented inference more efficient than connectionism-oriented.•More efficient and natural explanation compared to connectionist expert systems.

论文关键词：Neuro-symbolic approaches,Integrated intelligent systems,Rule-based reasoning and explanation,Hybrid intelligent systems,Hybrid expert systems

论文评审过程：Available online 4 February 2015.

论文官网地址：https://doi.org/10.1016/j.eswa.2015.01.068