{"id":{"repo_id":"uiuc","oai_identifier":"oai:www.ideals.illinois.edu:2142/69368"},"canonical_url":"https://search.dev.ndltd.org/etd/uiuc/oai:www.ideals.illinois.edu:2142/69368","repository":{"repo_id":"uiuc","name":"University of Illinois - Urbana-Champaign","base_url":"https://www.ideals.illinois.edu/oai-pmh"},"display":{"title":"Representing High-Level Knowledge Structures in Massively Parallel Networks","abstract":"Traditional artificial intelligence (AI) research has concentrated mostly on modeling high-level thought processes such as problem-solving and planning, and high-level representations such as rule-based heuristics and frame-based knowledge structures. Massively parallel networks, on the other hand, have been used mainly to model low-level perceptual processes such as vision, speech, associative memory, and learning. Recent research has started to bridge the gap between these disciplines. Massively parallel networks have many representational and computational advantages to bring to traditional AI work. These networks are very good at filling in partial information and at learning and representing subtle relationships among concepts. In addition, they provide a means to tightly integrate information from different sources as well as a model to encode parallel processing. However, many difficult issues need to be solved before massively parallel techniques can become more applicable and be able to complement traditional AI techniques. These issues include the problem of variable binding, multiple instantiations of knowledge structures, recursion, hierarchical abstraction, and temporal constraints.","abstract_html":"Traditional artificial intelligence (AI) research has concentrated mostly on modeling high-level thought processes such as problem-solving and planning, and high-level representations such as rule-based heuristics and frame-based knowledge structures. Massively parallel networks, on the other hand, have been used mainly to model low-level perceptual processes such as vision, speech, associative memory, and learning. Recent research has started to bridge the gap between these disciplines. Massively parallel networks have many representational and computational advantages to bring to traditional AI work. These networks are very good at filling in partial information and at learning and representing subtle relationships among concepts. In addition, they provide a means to tightly integrate information from different sources as well as a model to encode parallel processing. However, many difficult issues need to be solved before massively parallel techniques can become more applicable and be able to complement traditional AI techniques. These issues include the problem of variable binding, multiple instantiations of knowledge structures, recursion, hierarchical abstraction, and temporal constraints.","abstract_has_math":false,"creators":["Chun, Hon Wai"],"institution":"University of Illinois at Urbana-Champaign","degree_name":"Ph.D.","degree_level":"Dissertation","degree_discipline":"Electrical Engineering","degree_department":null,"school":null,"contributors":["Waltz, David L."],"advisors":[],"committee_chairs":[],"committee_members":[],"year":2014,"date_issued":"2014-12-15T19:05:23Z","date_published":"2014-12-15T19:05:23Z","updated_at":"2026-07-22T22:26:00Z","subjects":["Artificial Intelligence","Computer Science"],"languages":[],"rights":[],"rights_urls":[],"identifier_entries":[{"key":"dc:identifier","label":"Identifier","values":["(UMI)AAI8803002"],"render_values":[{"text":"(UMI)AAI8803002","href":null,"code":true}]}]},"links":{"outbound_url":"http://hdl.handle.net/2142/69368","outbound_label":"Handle","outbound_source":"dc:identifier"},"metadata_groups":[{"id":"people","label":"People","entries":[{"key":"dc:contributor","label":"Contributor","values":["Waltz, David L."]},{"key":"dc:creator","label":"Author","values":["Chun, Hon Wai"]}]},{"id":"academic_context","label":"Academic Context","entries":[{"key":"dc:date","label":"Dc Date","values":["2014-12-15T19:05:23Z","10000-01-01","1987"]},{"key":"dc:type","label":"Dc Type","values":["text"]},{"key":"thesis:degree_discipline","label":"Discipline","values":["Electrical Engineering"]},{"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":["Artificial Intelligence","Computer Science"]}]},{"id":"identifiers","label":"Identifiers","entries":[{"key":"dc:identifier","label":"Identifier","values":["http://hdl.handle.net/2142/69368","(UMI)AAI8803002"]}]},{"id":"additional","label":"Additional Metadata","entries":[{"key":"dc:description","label":"Description","values":["Traditional artificial intelligence (AI) research has concentrated mostly on modeling high-level thought processes such as problem-solving and planning, and high-level representations such as rule-based heuristics and frame-based knowledge structures. Massively parallel networks, on the other hand, have been used mainly to model low-level perceptual processes such as vision, speech, associative memory, and learning. Recent research has started to bridge the gap between these disciplines. Massively parallel networks have many representational and computational advantages to bring to traditional AI work. These networks are very good at filling in partial information and at learning and representing subtle relationships among concepts. In addition, they provide a means to tightly integrate information from different sources as well as a model to encode parallel processing. However, many difficult issues need to be solved before massively parallel techniques can become more applicable and be able to complement traditional AI techniques. These issues include the problem of variable binding, multiple instantiations of knowledge structures, recursion, hierarchical abstraction, and temporal constraints.","These problems are explored in this thesis through the presentation of massively parallel models for schema structures, an approach to defining knowledge modules, and a model to represent rules. The massively parallel representational techniques introduced in this thesis include a representation of constraints which has been used to model schemata with temporal sequence constraints, a representation of modular knowledge structures that have been used to model adaptive competition as well as interactions among higher-order concepts, a hybrid schema representation which combines connectionist value-passing with marker passing, and a hybrid natural language rule-based system. These techniques have been implemented and successfully tested in applications such as speech recognition and natural language understanding.","Made available in DSpace on 2014-12-15T19:05:23Z (GMT). No. of bitstreams: 1 8803002.pdf: 5788616 bytes, checksum: 26a7d1234371aefd9156dd541706cc9d (MD5) Previous issue date: 1987","Embargo set by: Seth Robbins for item 69534 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","125 p.","Thesis (Ph.D.)--University of Illinois at Urbana-Champaign, 1987."]},{"key":"dc:title","label":"Title","values":["Representing High-Level Knowledge Structures in Massively Parallel Networks"]}]}],"canonical_facts":{"dc:contributor":["Waltz, David L."],"dc:creator":["Chun, Hon Wai"],"dc:date":["2014-12-15T19:05:23Z","10000-01-01","1987"],"dc:description":["Traditional artificial intelligence (AI) research has concentrated mostly on modeling high-level thought processes such as problem-solving and planning, and high-level representations such as rule-based heuristics and frame-based knowledge structures. Massively parallel networks, on the other hand, have been used mainly to model low-level perceptual processes such as vision, speech, associative memory, and learning. Recent research has started to bridge the gap between these disciplines. Massively parallel networks have many representational and computational advantages to bring to traditional AI work. These networks are very good at filling in partial information and at learning and representing subtle relationships among concepts. In addition, they provide a means to tightly integrate information from different sources as well as a model to encode parallel processing. However, many difficult issues need to be solved before massively parallel techniques can become more applicable and be able to complement traditional AI techniques. These issues include the problem of variable binding, multiple instantiations of knowledge structures, recursion, hierarchical abstraction, and temporal constraints.","These problems are explored in this thesis through the presentation of massively parallel models for schema structures, an approach to defining knowledge modules, and a model to represent rules. The massively parallel representational techniques introduced in this thesis include a representation of constraints which has been used to model schemata with temporal sequence constraints, a representation of modular knowledge structures that have been used to model adaptive competition as well as interactions among higher-order concepts, a hybrid schema representation which combines connectionist value-passing with marker passing, and a hybrid natural language rule-based system. These techniques have been implemented and successfully tested in applications such as speech recognition and natural language understanding.","Made available in DSpace on 2014-12-15T19:05:23Z (GMT). No. of bitstreams: 1 8803002.pdf: 5788616 bytes, checksum: 26a7d1234371aefd9156dd541706cc9d (MD5) Previous issue date: 1987","Embargo set by: Seth Robbins for item 69534 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","125 p.","Thesis (Ph.D.)--University of Illinois at Urbana-Champaign, 1987."],"dc:identifier":["http://hdl.handle.net/2142/69368","(UMI)AAI8803002"],"dc:subject":["Artificial Intelligence","Computer Science"],"dc:title":["Representing High-Level Knowledge Structures in Massively Parallel Networks"],"dc:type":["text"],"thesis:degree_discipline":["Electrical Engineering"],"thesis:degree_level":["Dissertation"],"thesis:degree_name":["Ph.D."],"thesis:institution_name":["University of Illinois at Urbana-Champaign"]},"updated_at":"2026-07-22T22:26:00Z"}