Explanation-based learning:A problem solving perspective

Minton, Steven; Carbonell, Jaime G.; Knoblock, Craig A.; Kuokka, Daniel R.; Etzioni, Oren; Gil, Yolanda

doi:10.1016/0004-3702(89)90047-7

Cited by 164 publications

(78 citation statements)

References 11 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…A hybrid approach (Shavlik and Towell, 1989;Towell and Shavlik, 1994) initializes a potentially deep FNN through a domain theory in propositional logic, which may be acquired through explanation-based learning (Mitchell et al, 1986;DeJong and Mooney, 1986;Minton et al, 1989). The NN is then fine-tuned through BP (Sec.…”

Section: Ideas For Dealing With Long Time Lags and Deep Capsmentioning

confidence: 99%

Deep learning in neural networks: An overview

2015

View full text Add to dashboard Cite

In recent years, deep artificial neural networks (including recurrent ones) have won numerous contests in pattern recognition and machine learning. This historical survey compactly summarises relevant work, much of it from the previous millennium. Shallow and deep learners are distinguished by the depth of their credit assignment paths, which are chains of possibly learnable, causal links between actions and effects. I review deep supervised learning (also recapitulating the history of backpropagation), unsupervised learning, reinforcement learning & evolutionary computation, and indirect search for short programs encoding deep and large networks.LATEX source: http://www.idsia.ch/˜juergen/DeepLearning8Oct2014.tex Complete BIBTEX file (888 kB): http://www.idsia.ch/˜juergen/deep.bib Preface This is the preprint of an invited Deep Learning (DL) overview. One of its goals is to assign credit to those who contributed to the present state of the art. I acknowledge the limitations of attempting to achieve this goal. The DL research community itself may be viewed as a continually evolving, deep network of scientists who have influenced each other in complex ways. Starting from recent DL results, I tried to trace back the origins of relevant ideas through the past half century and beyond, sometimes using "local search" to follow citations of citations backwards in time. Since not all DL publications properly acknowledge earlier relevant work, additional global search strategies were employed, aided by consulting numerous neural network experts. As a result, the present preprint mostly consists of references. Nevertheless, through an expert selection bias I may have missed important work. A related bias was surely introduced by my special familiarity with the work of my own DL research group in the past quarter-century. For these reasons, this work should be viewed as merely a snapshot of an ongoing credit assignment process. To help improve it, please do not hesitate to send corrections and suggestions to juergen@idsia.ch.

show abstract

Section: Ideas For Dealing With Long Time Lags and Deep Capsmentioning

confidence: 99%

Deep learning in neural networks: An overview

2015

View full text Add to dashboard Cite

show abstract

“…The history of the prodigy architecture see Table 2.1 began circa 1986, when Minton and Carbonell implemented prodigy1, which became a testbed for their work on control rules Minton, 1988;Minton et al, 1989a . They concentrated on explanation-based learning of control knowledge and left few records of the original search engine.…”

Section: Historymentioning

confidence: 99%

Automatic Representation Changes in Problem Solving

Fink

1999

View full text Add to dashboard Cite

Public reporting burden for the collection of information is estimated to average 1 hour per response, including the time for reviewing instructions, searching existing data sources, gathering and maintaining the data needed, and completing and reviewing the collection of information. Send comments regarding this burden estimate or any other aspect of this collection of information, including suggestions for reducing this burden, to Washington Headquarters Services, Directorate for Information Operations and Reports, 1215 Jefferson Davis Highway, Suite 1204, Arlington VA 22202-4302. Respondents should be aware that notwithstanding any other provision of law, no person shall be subject to a penalty for failing to comply with a collection of information if it does not display a currently valid OMB control number. REPORT DATE JUN 19992. REPORT TYPE 3. DATES COVERED 00-00-1999 to 00-00-1999 TITLE AND SUBTITLE Automatic Representation Changes in Problem Solving5a. CONTRACT NUMBER 5b. GRANT NUMBER 5c. PROGRAM ELEMENT NUMBER 6. AUTHOR (S) 5d. PROJECT NUMBER 5e. TASK NUMBER 5f. WORK UNIT NUMBER PERFORMING ORGANIZATION NAME(S) AND ADDRESS(ES)Carnegie Mellon University,School of Computer Science,Pittsurgh,PA,152138. PERFORMING ORGANIZATION REPORT NUMBER SPONSORING/MONITORING AGENCY NAME(S) AND ADDRESS(ES) 10. SPONSOR/MONITOR'S ACRONYM(S) SPONSOR/MONITOR'S REPORT NUMBER(S) DISTRIBUTION/AVAILABILITY STATEMENTApproved for public release; distribution unlimited SUPPLEMENTARY NOTES ABSTRACTThe purpose of our research is to enhance the e ciency of AI problem solvers by automating representation changes. We have developed a system that improves description of input problems and selects an appropriate search algorithm for each given problem. Motivation Researchers have accumulated much evidence of the importance of appropriate representations for the e ciency of AI systems. The same problem may be easy or di cult, depending on the way we describe it and on the search algorithm we use. Previous work on automatic improvement of problem description has mostly been limited to the design of individual learning algorithms. The user has traditionally been responsible for the choice of algorithms appropriate for a given problem. We present a system that integrates multiple description-changing and problem-solving algorithms. The purpose of our work is to formalize the concept of representation, explore its role in problem solving, and con rm the following general hypothesis An e ective representation-changing system can be constructed out of three parts a library of problem-solving algorithms a library of algorithms that improve problem description by static analysis and learning a top-level control module that selects appropriate algorithms for each given problem. Representation-changing system We have supported this hypothesis by building a system that improves representations in the prodigy problem-solving architecture. The purpose of our research is to enhance the e ciency of AI problem solvers by automating representation change...

show abstract

“…ALPINE is a fully implemented system that generates abstraction hierarchies for the PRODIGY problem solver [46]. ALPINE is given a problem space specification and a problem to be solved and it produces a problem-specific abstraction hierarchy for the given problem.…”

Section: Generating Abstractions In Alpinementioning

confidence: 99%

“…The abstractions are based on the ordered monotonicity property, which guarantees that the structure of the abstract plan will be preserved while the plan is refined. This algorithm is implemented in the ALPINE system and the abstraction hierarchies generated by ALPINE are used in a version of the PRODIGY problem solver [9,46] that was extended to plan hierarchically [351. This article presents experimental results that demonstrate that ALPINE's abstractions provide significant reductions in search over planning without the use of abstraction.…”

Section: Introductionmentioning

confidence: 99%