Department of Computer Engineering
S E M I N A R
Building Foundations For General Artificial Intelligence
Nowadays, trends in AI focus on creating domain-specific models for particular human cognitive abilities or tasks and it seems that the aim of creating a general intelligence framework has been sidelined by much of the community. As a result new subfields are created for tools that often cannot singularly accomplish unified human cognition. The idea that these various domain-specific models can be merged without any deficiencies also seems unrealistic. In order for a model to be cognitively plausible it must account for seemingly conflicting cognitive abilities, such as being goal-oriented while at the same time having a highly interruptible "attention span". While our long-term goal is to establish a cognitively plausible general intelligence framework, presently we aim to examine the advantages and disadvantages of the existing models and suggest alternative foundations. We hope to provide mechanisms for an associationist/connectionist model which we believe can act as a basis for various cognitive abilities.
DATE: May 16, 2005, Monday @ 15:40
PLACE: EA 409