Vector Symbolic Architectures: A New Building Material for Artificial General Intelligence

We provide an overview of Vector Symbolic Architectures (VSA), a class of structured associative memory models that offers a number of desirable features for artificial general intelligence. By directly encoding structure using familiar, computationally efficient algorithms, VSA bypasses many of the problems that have consumed unnecessary effort and attention in previous connectionist work. Example applications from opposite ends of the AI spectrum

• Type: Conference
• Year: 2008
• Where: AGI
• Authors: Simon D. Levy, Ross Gayler
• Keywords: AGI 2008, Artificial Intelligence, Associative Memory, Structured Associative Memory, Vector Symbolic Architectures