Publication Type

Journal Article

Version

acceptedVersion

Publication Date

3-2016

Abstract

Semantic memory plays a critical role in reasoning and decision making. It enables an agent to abstract useful knowledge learned from its past experience. Based on an extension of fusion adaptive resonance theory network, this paper presents a novel self-organizing memory model to represent and learn various types of semantic knowledge in a unified manner. The proposed model, called fusion adaptive resonance theory for multimemory learning, incorporates a set of neural processes, through which it may transfer knowledge and cooperate with other long-term memory systems, including episodic memory and procedural memory. Specifically, we present a generic learning process, under which various types of semantic knowledge can be consolidated and transferred from the specific experience encoded in episodic memory. We also identify and formalize two forms of memory interactions between semantic memory and procedural memory, through which more effective decision making can be achieved. We present experimental studies, wherein the proposed model is used to encode various types of semantic knowledge in different domains, including a first-person shooting game called Unreal Tournament, the Toads and Frogs puzzle, and a strategic game known as StarCraft Broodwar. Our experiments show that the proposed knowledge transfer process from episodic memory to semantic memory is able to extract useful knowledge to enhance the performance of decision making. In addition, cooperative interaction between semantic knowledge and procedural skills can lead to a significant improvement in both learning efficiency and performance of the learning agents.

Keywords

semantic memory, learning agents, memory interactions, adaptive resonance theory

Discipline

Databases and Information Systems | OS and Networks | Software Engineering

Research Areas

Data Science and Engineering

Publication

IEEE Transactions on Systems, Man and Cybernetics, Part A: Systems and Humans

Volume

47

Issue

11

First Page

47

Last Page

11

ISSN

1083-4427

Identifier

10.1109/TSMC.2016.2531683

Publisher

Institute of Electrical and Electronics Engineers (IEEE)

Additional URL

https://doi.org/10.1109/TSMC.2016.2531683

Download

Share

COinS