A Bayesian Computational Cognitive Model

Computational cognitive modeling has recently emerged as one of the hottest issues in the AI area. Both symbolic approaches and connectionist approaches present their merits and demerits. Although Bayesian method is suggested to incorporate advantages of the two kinds of approaches above, there is no feasible Bayesian computational model concerning the entire cognitive process by now. In this paper, we propose a variation of traditional Bayesian network, namely Globally Connected and Locally Autonomic Bayesian Network (GCLABN), to formally describe a plausible cognitive model. The model adopts a unique knowledge representation strategy, which enables it to encode both symbolic concepts and their relationships within a graphical structure, and to generate cognition via a dynamic oscillating process rather than a straightforward reasoning process like traditional approaches. Then a simple simulation is employed to illustrate the properties and dynamic behaviors of the model. All these traits of the model are coincident with the recently discovered properties of the human cognitive process.

Authors

• Zhiwei Shi
• Hong Hu 0001
• Zhongzhi Shi

Keywords

No keywords are indexed for this paper.