A foundational architecture for artificial general intelligence

Document Type: 
Article
Article Type: 
Theoretical
Disciplines: 
Artificial intelligence
Topics: 
Other
Date of Issue: 
2007
Authors: 
Stan Franklin
Editors: 
Ben Goertzel and Pei Wang
Journal/Publication Title: 
Proceedings of the AGI Workshop 2006
Page Range: 
36-54
Publisher: 
IOS Press
Place of Publication: 
Amsterdam
Official URL: 
http://ccrg.cs.memphis.edu/assets/papers/draft%2010-2-06.doc
Publish status: 
Published
Abstract: 
Implementing and fleshing out a number of psychological and neuroscience theories of cognition, the LIDA conceptual model aims at being a cognitive “theory of everything.” With modules or processes for perception, working memory, episodic memories, “consciousness,” procedural memory, action selection, perceptual learning, episodic learning, deliberation, volition, and non-routine problem solving, the LIDA model is ideally suited to provide a working ontology that would allow for the discussion, design, and comparison of AGI systems. The LIDA architecture is based on the LIDA cognitive cycle, a sort of “cognitive atom.” The more elementary cognitive modules and processes play a role in each cognitive cycle. Higher-level processes are performed over multiple cycles. In addition to giving a quick overview of the LIDA conceptual model, and its underlying computational technology, we argue for the LIDA architecture’s role as a foundational architecture for an AGI. Finally, lessons For AGI researchers drawn from the model and its architecture are discussed.
AttachmentSize
draft 10-2-06.doc254.5 KB