Artificial Intelligence - Special volume on qualitative reasoning about physical systems
SOAR: an architecture for general intelligence
Artificial Intelligence
The structure-mapping engine: algorithm and examples
Artificial Intelligence
Compositional modeling: finding the right model for the job
Artificial Intelligence - Special issue: Qualitative reasoning about physical systems II
Building problem solvers
Derivational Analogy in PRODIGY: Automating Case Acquisition, Storage, and Utilization
Machine Learning - Special issue on case-based reasoning
Case-based reasoning
Artificial Intelligence
Automated modeling for answering prediction questions: selecting the time scale and system boundary
AAAI'94 Proceedings of the twelfth national conference on Artificial intelligence (vol. 2)
Analogy in Inductive Theorem Proving
Journal of Automated Reasoning
A Randomized ANOVA Procedure for Comparing Performance Curves
ICML '98 Proceedings of the Fifteenth International Conference on Machine Learning
Companion cognitive systems: a step toward human-level AI
AI Magazine - Special issue on achieving human-level AI through integrated systems and research
Enhancing intelligent agents with episodic memory
Enhancing intelligent agents with episodic memory
Companion Cognitive Systems: Design Goals and Lessons Learned So Far
IEEE Intelligent Systems
Value-function-based transfer for reinforcement learning using structure mapping
AAAI'06 Proceedings of the 21st national conference on Artificial intelligence - Volume 1
Strategy variations in analogical problem solving
AAAI'06 Proceedings of the 21st national conference on Artificial intelligence - Volume 1
Solving everyday physical reasoning problems by analogy using sketches
AAAI'05 Proceedings of the 20th national conference on Artificial intelligence - Volume 1
Measuring the level of transfer learning by an AP physics problem-solver
AAAI'07 Proceedings of the 22nd national conference on Artificial intelligence - Volume 1
Achieving far transfer in an integrated cognitive architecture
AAAI'08 Proceedings of the 23rd national conference on Artificial intelligence - Volume 3
Solving mechanics problems using meta-level inference
IJCAI'79 Proceedings of the 6th international joint conference on Artificial intelligence - Volume 2
Representations of knowledge in a program for solving physics problems
IJCAI'77 Proceedings of the 5th international joint conference on Artificial intelligence - Volume 1
Multiples representations of knowledge in a mechanics problem-solver
IJCAI'77 Proceedings of the 5th international joint conference on Artificial intelligence - Volume 1
An examination of the third stage in the analogy process: verification-based analogical learning
IJCAI'87 Proceedings of the 10th international joint conference on Artificial intelligence - Volume 1
Analogical learning in a turn-based strategy game
IJCAI'07 Proceedings of the 20th international joint conference on Artifical intelligence
Transfer learning in real-time strategy games using hybrid CBR/RL
IJCAI'07 Proceedings of the 20th international joint conference on Artifical intelligence
A Categorization of KR&R Methods for Requirement Analysis of a Query Answering Knowledge Base
Proceedings of the 2010 conference on Formal Ontology in Information Systems: Proceedings of the Sixth International Conference (FOIS 2010)
The challenge of complexity for cognitive systems
Cognitive Systems Research
Hi-index | 0.00 |
Transfer learning is the ability to apply previously learned knowledge to new problems or domains. In qualitative reasoning, model formulation is the process of moving from the unruly, broad set of concepts used in everyday life to a concise, formal vocabulary of abstractions, assumptions, causal relationships, and models that support problem-solving. Approaching transfer learning from a model formulation perspective, we found that analogy with examples can be used to learn how to solve AP Physics style problems. We call this process analogical model formulation and implement it in the Companion cognitive architecture. A Companion begins with some basic mathematical skills, a broad common sense ontology, and some qualitative mechanics, but no equations. The Companion uses worked solutions, explanations of example problems at the level of detail appearing in textbooks, to learn what equations are relevant, how to use them, and the assumptions necessary to solve physics problems. We present an experiment, conducted by the Educational Testing Service, demonstrating that analogical model formulation enables a Companion to learn to solve AP Physics style problems. Across six different variations of relationships between base and target problems, or transfer levels, a Companion exhibited a 63% improvement in initial performance. While already a significant result, we describe an in-depth analysis of this experiment to pinpoint the causes of failures. Interestingly, the sources of failures were primarily due to errors in the externally generated problem and worked solution representations as well as some domain-specific problem-solving strategies, not analogical model formulation. To verify this, we describe a second experiment which was performed after fixing these problems. In this second experiment, a Companion achieved a 95.8% improvement in initial performance due to transfer, which is nearly perfect. We know of no other problem-solving experiments which demonstrate performance of analogical learning over systematic variations of relationships between problems at this scale.