Modeling the Evolution of Knowledge in Learning Systems

Abhishek Sharma, Kenneth D. Forbus

Research output: Contribution to conferencePaperpeer-review


How do reasoning systems that learn evolve over time? What are the properties of different learning strategies? 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 large knowledge-based systems evolve: Create a small knowledge base by ablating a large KB, and simulate learning by incrementally re-adding facts, using different strategies to simulate types of learners. For each iteration, reasoning properties (including number of questions answered and run time) are collected, to explore how learning strategies and reasoning interact. We describe several experiments with the inverse ablation model, examining how two different learning strategies perform. Our results suggest that different concepts show different rates of growth, and that the density and distribution of facts that can be learned are important parameters for modulating the rate of learning.

Original languageEnglish (US)
Number of pages7
StatePublished - 2012
Event26th AAAI Conference on Artificial Intelligence, AAAI 2012 - Toronto, Canada
Duration: Jul 22 2012Jul 26 2012


Conference26th AAAI Conference on Artificial Intelligence, AAAI 2012

ASJC Scopus subject areas

  • Artificial Intelligence


Dive into the research topics of 'Modeling the Evolution of Knowledge in Learning Systems'. Together they form a unique fingerprint.

Cite this