APT, A Cooperative ML System

Claire Nedelec

In this paper, we present APT system as an example of a learning apprentice that learns from examples of expert problem-solving. Learning in APT is not fully automated but cooperative, so that APT is partially in charge of tasks that are usually left to the user, such as acquisition of examples, revision of input data and validation of learned knowledge. The efficiency of APT cooperation relies on the fact that it is based on a problem-solving context that is common to both the expert and the system because its exploits examples of expert problem-solving.


This page is copyrighted by AAAI. All rights reserved. Your use of this site constitutes acceptance of all of AAAI's terms and conditions and privacy policy.