Achieving Far Transfer in an Integrated Cognitive Architecture
Abstract
Transfer is the ability to employ knowledge acquired in one task to improve performance in another. We study transfer in the context of the ICARUS cognitive architec-ture, which supplies diverse capabilities for execution, inference, planning, and learning. We report on an exten-sion to ICARUS called representation mapping that trans-fers structured skills and concepts between disparate tasks that may not even be expressed with the same symbol set. We show that representation mapping is naturally inte-grated into ICARUS ’ cognitive processing loop, resulting in a system that addresses a qualitatively new class of problems by considering the relevance of past experience to current goals.
Cite
Text
Shapiro et al. "Achieving Far Transfer in an Integrated Cognitive Architecture." AAAI Conference on Artificial Intelligence, 2008.Markdown
[Shapiro et al. "Achieving Far Transfer in an Integrated Cognitive Architecture." AAAI Conference on Artificial Intelligence, 2008.](https://mlanthology.org/aaai/2008/shapiro2008aaai-achieving/)BibTeX
@inproceedings{shapiro2008aaai-achieving,
title = {{Achieving Far Transfer in an Integrated Cognitive Architecture}},
author = {Shapiro, Daniel G. and Könik, Tolga and O'Rorke, Paul},
booktitle = {AAAI Conference on Artificial Intelligence},
year = {2008},
pages = {1325-1330},
url = {https://mlanthology.org/aaai/2008/shapiro2008aaai-achieving/}
}