Learner

LEARNER allows you to teach a computer things that you know and then ask it questions about what it has learner from everyone.

We hope that by capturing things people know and capturing "how they conclude things from other things" we can pave the way to smarter, easier to use information repositories and easier to use computers.

More formally, LEARNER is a system for capturing declarative knowledge and inference rules. A fundamental feature of the system is to "tease" the knowledge out of the user by posing plausible questions.

Importantly, the number and quality of follow-up questions LEARNER poses increases as the amount of knowledge in the system increases. The approach is to intelligently re-use the knowledge that users put in to get more good information. The mechanisms of "intelligently re-using inputted knowledge" are necessarily diverse.

LEARNER is open source and has a general plug-in architecture for question-posing modules.

Teach Learner

1001 Questions: You can now play a free online game of knowledge that uses the Learner reasoning engine!

Get Documentation

One source of documentation on the project is the Learner Manual. Another is the PhD thesis proposal. It includes a motivation for the project, a user's guide, and a programmers guide.

learner-manual .html (107K) .pdf (238K) .ps (288K)

Download Code

Do you believe the Learner can be made better? Want to try your hand at making a plug-in that adds smarts to the system?

Learner source code is available for download for free. The distribution is under the following BSD-style license.

The project CVS and released files are here at SourceForge.

Contact Us

This is a young and growing project looking for contributors. If you have an idea or a suggestion, send us email.

To provide you with the best support and get your development help, we are using services SourceForge extends to Open Source projects.	To provide the best in distributing the accumulated data, we are in the process of becoming a part of the Open Mind initiative.	To provide the best knowledge acquisition tool and have the largest repository, we are using data gathered by Open Mind Commonsense.