<< 1 >>
Rating: 
Summary: A significant advance in Artificial Intelligence
Review: This book describes a theory of how a computer program might be implemented to learn and use new concepts that have not been programmed into it. It uses the theories and observations of Jean Piaget, theories of learning in infants and children, as a basis on which to formulate a new vocabulary which allows us to talk in concrete terms about formerly vague and confusing concepts which are central to the understanding and engineering of intelligence. The central proposition of the theory is the "schema mechanism", which describes an elegant and technically and philosophically satisfying mechanism for how a learning system can incorporate new and previously incomprehensible fragments of knowledge, to build new and robust descriptions of objects and the effects of actions upon them. These new "schemas" can be incorporated into yet more complex descriptions of the environment, providing a robust and self-consistent system that can bootstrap itself to higher and higher levels of competence and intelligence, without need for any external intervention from the programmer except in the form of "teaching" the system as you would a real human infant. I believe this book represents the largest advance in artificial intelligence theory since Alan Turing described the first universal computer, and is comparable in importance to the inventions of Algebra and Calculus as notational systems and technologies which allowed progress in the fields of science and engineering.
<< 1 >>
| 
