{"id":{"repo_id":"uiuc","oai_identifier":"oai:www.ideals.illinois.edu:2142/69590"},"canonical_url":"https://search.dev.ndltd.org/etd/uiuc/oai:www.ideals.illinois.edu:2142/69590","repository":{"repo_id":"uiuc","name":"University of Illinois - Urbana-Champaign","base_url":"https://www.ideals.illinois.edu/oai-pmh"},"display":{"title":"Generalizing the Structure of Explanations in Explanation-Based Learning","abstract":"Explanation-based learning is a recently developed approach to concept acquisition by computer. In this type of machine learning, a specific problem's solution is generalized into a form that can later be used to solve conceptually similar problems. A number of explanation-based generalization algorithms have been developed. Most do not alter the structure of the explanation of the specific problems--no additional objects nor inference rules are incorporated. Instead, these algorithms generalize by converting constants in the observed example to variables with constraints. However, many important concepts, in order to be properly learned, require that the structure of explanations be generalized. This can involve generalizing such things as the number of entities involved in a concept or the number of times some action is performed. For example, concepts such as momentum and energy conservation apply to arbitrary numbers of physical objects, clearing the top of a desk can require an arbitrary number of object relocations, and setting a table can involve an arbitrary number of guests.","abstract_html":"Explanation-based learning is a recently developed approach to concept acquisition by computer. In this type of machine learning, a specific problem's solution is generalized into a form that can later be used to solve conceptually similar problems. A number of explanation-based generalization algorithms have been developed. Most do not alter the structure of the explanation of the specific problems--no additional objects nor inference rules are incorporated. Instead, these algorithms generalize by converting constants in the observed example to variables with constraints. However, many important concepts, in order to be properly learned, require that the structure of explanations be generalized. This can involve generalizing such things as the number of entities involved in a concept or the number of times some action is performed. For example, concepts such as momentum and energy conservation apply to arbitrary numbers of physical objects, clearing the top of a desk can require an arbitrary number of object relocations, and setting a table can involve an arbitrary number of guests.","abstract_has_math":false,"creators":["Shavlik, Jude William"],"institution":"University of Illinois at Urbana-Champaign","degree_name":"Ph.D.","degree_level":"Dissertation","degree_discipline":"Computer Science","degree_department":null,"school":null,"contributors":["DeJong, Gerald F."],"advisors":[],"committee_chairs":[],"committee_members":[],"year":2014,"date_issued":"2014-12-15T19:26:03Z","date_published":"2014-12-15T19:26:03Z","updated_at":"2026-07-22T22:26:01Z","subjects":["Education, Technology of","Artificial Intelligence","Computer Science"],"languages":[],"rights":[],"rights_urls":[],"identifier_entries":[{"key":"dc:identifier","label":"Identifier","values":["(UMI)AAI8815422"],"render_values":[{"text":"(UMI)AAI8815422","href":null,"code":true}]}]},"links":{"outbound_url":"http://hdl.handle.net/2142/69590","outbound_label":"Handle","outbound_source":"dc:identifier"},"metadata_groups":[{"id":"people","label":"People","entries":[{"key":"dc:contributor","label":"Contributor","values":["DeJong, Gerald F."]},{"key":"dc:creator","label":"Author","values":["Shavlik, Jude William"]}]},{"id":"academic_context","label":"Academic Context","entries":[{"key":"dc:date","label":"Dc Date","values":["2014-12-15T19:26:03Z","10000-01-01","1988"]},{"key":"dc:type","label":"Dc Type","values":["text"]},{"key":"thesis:degree_discipline","label":"Discipline","values":["Computer Science"]},{"key":"thesis:degree_level","label":"Degree Level","values":["Dissertation"]},{"key":"thesis:degree_name","label":"Degree Name","values":["Ph.D."]},{"key":"thesis:institution_name","label":"Thesis Institution Name","values":["University of Illinois at Urbana-Champaign"]}]},{"id":"subjects_keywords","label":"Subjects and Keywords","entries":[{"key":"dc:subject","label":"Dc Subject","values":["Education, Technology of","Artificial Intelligence","Computer Science"]}]},{"id":"identifiers","label":"Identifiers","entries":[{"key":"dc:identifier","label":"Identifier","values":["http://hdl.handle.net/2142/69590","(UMI)AAI8815422"]}]},{"id":"additional","label":"Additional Metadata","entries":[{"key":"dc:description","label":"Description","values":["Explanation-based learning is a recently developed approach to concept acquisition by computer. In this type of machine learning, a specific problem's solution is generalized into a form that can later be used to solve conceptually similar problems. A number of explanation-based generalization algorithms have been developed. Most do not alter the structure of the explanation of the specific problems--no additional objects nor inference rules are incorporated. Instead, these algorithms generalize by converting constants in the observed example to variables with constraints. However, many important concepts, in order to be properly learned, require that the structure of explanations be generalized. This can involve generalizing such things as the number of entities involved in a concept or the number of times some action is performed. For example, concepts such as momentum and energy conservation apply to arbitrary numbers of physical objects, clearing the top of a desk can require an arbitrary number of object relocations, and setting a table can involve an arbitrary number of guests.","Two theories of extending explanations during the generalization process have been developed and computer implementations have been created to computationally test these approaches. The Physics 101 system utilizes characteristics of mathematically-based problem solving to extend mathematical calculations in a psychologically-plausible way, while the BAGGER system implements a domain-independent approach to generalizing explanation structures. Both of these systems are described and the details of their algorithms presented. Several examples of learning in each system are discussed. An approach to the operationality/generality trade-off and an empirical analysis of explanation-based learning are also presented. The computer experiments demonstrate the value of generalizing explanation structures in particular, and of explanation-based learning in general. These experiments also demonstrate the advantages of learning by observing the intelligent behavior of external agents. Several open research issues in generalizing the structure of explanations and related approaches to this problem are discussed. This research brings explanation-based learning closer to its goal of being able to acquire the full concept inherent in the solution to a specific problem.","Made available in DSpace on 2014-12-15T19:26:03Z (GMT). No. of bitstreams: 1 8815422.pdf: 11336632 bytes, checksum: 59585f6eac639c8ff95c544d041463f3 (MD5) Previous issue date: 1988","Embargo set by: Seth Robbins for item 69756 Lift date: Forever Reason: Restricted to the U of I community idenfinitely during batch ingest of legacy ETDs","Restricted to the U of I community idenfinitely during batch ingest of legacy ETDs","U of I Only","290 p.","Thesis (Ph.D.)--University of Illinois at Urbana-Champaign, 1988."]},{"key":"dc:title","label":"Title","values":["Generalizing the Structure of Explanations in Explanation-Based Learning"]}]}],"canonical_facts":{"dc:contributor":["DeJong, Gerald F."],"dc:creator":["Shavlik, Jude William"],"dc:date":["2014-12-15T19:26:03Z","10000-01-01","1988"],"dc:description":["Explanation-based learning is a recently developed approach to concept acquisition by computer. In this type of machine learning, a specific problem's solution is generalized into a form that can later be used to solve conceptually similar problems. A number of explanation-based generalization algorithms have been developed. Most do not alter the structure of the explanation of the specific problems--no additional objects nor inference rules are incorporated. Instead, these algorithms generalize by converting constants in the observed example to variables with constraints. However, many important concepts, in order to be properly learned, require that the structure of explanations be generalized. This can involve generalizing such things as the number of entities involved in a concept or the number of times some action is performed. For example, concepts such as momentum and energy conservation apply to arbitrary numbers of physical objects, clearing the top of a desk can require an arbitrary number of object relocations, and setting a table can involve an arbitrary number of guests.","Two theories of extending explanations during the generalization process have been developed and computer implementations have been created to computationally test these approaches. The Physics 101 system utilizes characteristics of mathematically-based problem solving to extend mathematical calculations in a psychologically-plausible way, while the BAGGER system implements a domain-independent approach to generalizing explanation structures. Both of these systems are described and the details of their algorithms presented. Several examples of learning in each system are discussed. An approach to the operationality/generality trade-off and an empirical analysis of explanation-based learning are also presented. The computer experiments demonstrate the value of generalizing explanation structures in particular, and of explanation-based learning in general. These experiments also demonstrate the advantages of learning by observing the intelligent behavior of external agents. Several open research issues in generalizing the structure of explanations and related approaches to this problem are discussed. This research brings explanation-based learning closer to its goal of being able to acquire the full concept inherent in the solution to a specific problem.","Made available in DSpace on 2014-12-15T19:26:03Z (GMT). No. of bitstreams: 1 8815422.pdf: 11336632 bytes, checksum: 59585f6eac639c8ff95c544d041463f3 (MD5) Previous issue date: 1988","Embargo set by: Seth Robbins for item 69756 Lift date: Forever Reason: Restricted to the U of I community idenfinitely during batch ingest of legacy ETDs","Restricted to the U of I community idenfinitely during batch ingest of legacy ETDs","U of I Only","290 p.","Thesis (Ph.D.)--University of Illinois at Urbana-Champaign, 1988."],"dc:identifier":["http://hdl.handle.net/2142/69590","(UMI)AAI8815422"],"dc:subject":["Education, Technology of","Artificial Intelligence","Computer Science"],"dc:title":["Generalizing the Structure of Explanations in Explanation-Based Learning"],"dc:type":["text"],"thesis:degree_discipline":["Computer Science"],"thesis:degree_level":["Dissertation"],"thesis:degree_name":["Ph.D."],"thesis:institution_name":["University of Illinois at Urbana-Champaign"]},"updated_at":"2026-07-22T22:26:01Z"}