When Will Machines Learn?
Why don’t our learning programs just keep on going and become generally intelligent? The source of the problem is that most of our learning occurs at the fringe of what we already know. The more you know, the more (and faster) you can learn.
KeywordsBrittle Editing Metaphor
Unable to display preview. Download preview PDF.
- Hayes, P. 1985. Naive physics manifesto. In Hobbs and Moore (Eds.), Formal theories of the common sense world. Norwood: Ablex.Google Scholar
- Lenat, D., and Guha, R.Y. 1988. The world according to CYC. (MCC Technical Report Number ACA-AI-300-88.) An expanded version of this, in book form, is (in press) Building large knowledge-based systems: Representation and inference in the CYC project. Addison-Wesley.Google Scholar