Explanation-Based Learning: An Alternative View

By Gerald DeJong, Raymond J. Mooney. 1986

Subfields: Representation & Self-Supervised Learning, Optimization & Training

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Representation & Self-Supervised Learning

In Optimization & Training

Citations in the corpus

Joint Concept Learning and Semantic Parsing from Natural Language Explanations (2017, background): “Earlier work on Explanation-based learning (Mitchell et al., 1986; DeJong and Mooney, 1986) Semantic interpretation of language has been explored in diverse domains.”
Deep learning in neural networks: An overview (2014, methodology): “A hybrid approach (Shavlik & Towell, 1989; Towell & Shavlik, 1994) initializes a potentially deep FNN through adomain theory in propositional logic, which may be acquired through explanationbased learning (DeJong & Mooney, 1986; Minton et al., 1989; Mitchell, Keller, & Kedar-Cabelli, 1986).”
Teaching Machine Comprehension with Compositional Explanations (2020, background): “One strength of human cognition is the ability to generalize from relatively few examples; shown only a few instances of a problem and solution, humans often deduce patterns more readily than a machine, typically by bringing to bear a wealth of background information about what “really matters” in e”
The changing science of machine learning (2011, background): “Many early programs embedded learning methods within sophisticated systems that carried out multi-step reasoning, heuristic problem solving, language understanding, or other complex cognitive activities (e.g., DeJong and Mooney 1986; Laird et al. 1986).”
Learning logical definitions from relations (1990, background): “Proof also is the central operation in all explanation-based learners (Mitchell et al., 1986; DeJong and Mooney, 1986).”
Introduction to the Special Issue on Explanation in Case-Based Reasoning (2005, background): “For example, explanations of problem circumstances may help the system to choose appropriate responses and may also help to guide learning (DeJong and Mooney 1986; Mitchell et al., 1986).”
Learning Semantic Parsers: An Important but Under-Studied Problem (2004, background): “…the mid 1980's focused on attempting to relieve the knowledgeengineering bottleneck by using explanation-based learning (EBL) to automatically acquire the larger knowledge structures (scripts or schemas) needed for narrative understanding (DeJong 1981; Mooney & DeJong 1985; DeJong & Mooney 1986).”
A Preliminary Survey of Explanation Facilities of AI-Based Design Support Approaches and Tools (2018, unknown): “Explanationbased generalization [9] is an approach for generalization of training examples in machine learning using explanation-based learning [5], an approach for supervised learning by explaining the results of the training (e.”
WorldTree V2: A Corpus of Science-Domain Structured Explanations and Inference Patterns supporting Multi-Hop Inference (2020, methodology): “As such, a potential partial solution to the problem of many-fact multi-hop inference may be in using large multi-fact templates similar to schema or semantic frames (Schank and Abelson, 1977; Minsky, 1974), but derived from explanations, similar to approaches for explanation-based learning (DeJong ”
Acquiring Recursive and Iterative Concepts with Explanation-Based Learning (1990, methodology): “BAGGER: An EBL system that extends and generalizes explanations.”
A new representation and associated algorithms for generalized planning (2011, background): “In explanation based learning (EBL) [8], a proof or an explanation of a solution is generalized to be applicable to different problem instances.”
Relational Reinforcement Learning An Overview (2004, background): “The proof is then generalized to construct a description of states which can be solved in the same way (Mitchell et al., 19866 DeJong & Mooney, 1986).”