TY - GEN
T1 - Modeling the evolution of knowledge and reasoning in learning systems
AU - Sharma, Abhishek
AU - Forbus, Kenneth D
PY - 2010
Y1 - 2010
N2 - How do reasoning systems that learn evolve over time? Characterizing the evolution of these systems is important for understanding their limitations and gaining insights into the interplay between learning and reasoning. We describe an inverse ablation model for studying how learning and reasoning interact: Create a small knowledge base by ablation, and incrementally re-add facts, collecting snapshots of reasoning performance of the system to measure properties of interest. Experiments with this model suggest that different concepts show different rates of growth, and that the density of facts is an important parameter for modulating the rate of learning.
AB - How do reasoning systems that learn evolve over time? Characterizing the evolution of these systems is important for understanding their limitations and gaining insights into the interplay between learning and reasoning. We describe an inverse ablation model for studying how learning and reasoning interact: Create a small knowledge base by ablation, and incrementally re-add facts, collecting snapshots of reasoning performance of the system to measure properties of interest. Experiments with this model suggest that different concepts show different rates of growth, and that the density of facts is an important parameter for modulating the rate of learning.
UR - http://www.scopus.com/inward/record.url?scp=79960112514&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=79960112514&partnerID=8YFLogxK
M3 - Conference contribution
AN - SCOPUS:79960112514
SN - 9781577354840
T3 - AAAI Fall Symposium - Technical Report
SP - 102
EP - 107
BT - Commonsense Knowledge - Papers from the AAAI Fall Symposium, Technical Report
PB - AI Access Foundation
T2 - 2010 AAAI Fall Symposium
Y2 - 11 November 2010 through 13 November 2010
ER -