VARIAC: an Autogenous Cognitive Architecture

Learning theory and programs to date are inductively bounded: they can be described as "wind-up toys" which can only learn the kinds of things that their designers envisioned. We conjecture [1] that general intelligence involves an unbounded learning ability. VARIAC is an experimental cognitive architecture designed to learn by modifying and extending itself, including its ability to learn, so that it can learn to become a better learner. Keywords. autogeny, learning, cognitive architectures, automatic programming Rationale

• Type: Conference
• Year: 2008
• Where: AGI
• Authors: J. Storrs Hall
• Keywords: AGI 2008, Artificial Intelligence, Cognitive Architectures, Unbounded Learning Ability, Wind-up Toys