The ECHO Project at ISI


Memory-Based Meta-Level Reasoning for Interactive Knowledge Capture

Description

ECHO (mEta-Cognitive History analysis and Organization) is a memory-based meta-level reasoning tool for interactive knowledge capture. It estimates the confidence level of learned knowledge using past problem solving episodes and provides suggestions to improve the knowledge and make the problem solving more successful.

More-->

Status

This project started in 2004.

More-->

Research

Memory-Based Meta-Level Reasoning for Interactive Knowledge Capture, Evaluating Status of Learned Knowledge using Past Problem Solving Episodes.

More -->

Publications

"Incorporating tutoring principles into interactive knowledge acquisition", Jihie Kim, Yolanda Gil, Marc Spraragen. In International Journal of Human-Computer Studies Volume 65, Issue 10, October 2007, Pages 852-872

"Memory-Based Meta-Level Reasoning for Interactive Knowledge Capture", Jihie Kim. In Proceedings of AAAI Spring Symposium on Metacognition in Computation, 2005

"From Reflection to Interaction: Use of Memory in Interactive Knowledge Acquisition", Jihie Kim. In Proceedings of CogSci-2005

More publications -->

Group Members:

DARPA's Personalized Assistant that Learns (PAL)
Department of Defense