Title: Contemporary cognitive architectures: a comparative study of structures and adaptability
Authors: Marx Rajangam; Chitra Annamalai
Addresses: Department of Computer Science and Engineering, PSG College of Technology, Coimbatore, 641004, India ' Department of Computer Applications, PSG College of Technology, Coimbatore, 641004, India
Abstract: Cognitive architectures aim to provide blueprints for achieving artificial general intelligence (AGI). Cognitive models that can provide crucial clues to the working of human mind are typically built on top of cognitive architectures. This paper reviews contemporary cognitive architectures including Soar, ACT-R, CLARION, OpenCog Prime and ICARUS in terms of architecture and components, knowledge and representation, learning and adaptability, and memory models. It then evaluates these architectures based on certain evaluation criteria. In addition, this paper reviews recent research focus in these architectures and their usage in real-world applications. Finally, this paper discusses the trends and challenges ahead in building effective cognitive architectures.
Keywords: cognitive architectures; cognitive models; artificial general intelligence; AGI; intelligent agents; Soar; ACT-R; CLARION; ICARUS; OpenCog Prime; cognition; comparative study; adaptability; agent-based systems; multi-agent systems; MAS; artificial intelligence.
DOI: 10.1504/IJAISC.2016.10002229
International Journal of Artificial Intelligence and Soft Computing, 2016 Vol.5 No.4, pp.263 - 284
Received: 17 Oct 2015
Accepted: 12 May 2016
Published online: 05 Jan 2017 *