{"id":{"repo_id":"texas-state","oai_identifier":"oai:digital.library.txst.edu:10877/9559"},"canonical_url":"https://search.dev.ndltd.org/etd/texas-state/oai:digital.library.txst.edu:10877/9559","repository":{"repo_id":"texas-state","name":"Texas State University","base_url":"https://digital.library.txst.edu/server/oai/request"},"display":{"title":"Evolving Learning Neural Networks","abstract":"Supervised learning has long been used to modify the artificial neural network in order to perform classification tasks. However, the standard fully connected layered design is often inadequate when performing such tasks. We show that evolution can be used to design an artificial neural network that learns faster and more accurately. By evolving artificial neural networks within a dynamic environment, the artificial neural network is forced to use learning. This strategy combined with incremental evolution produces an artificial neural network that outperforms the standard fully-connected layered design. The resulting artificial neural network can learn to solve an entire domain of problems, including those of lesser complexity. Evolution alone can be used to create a network that solves a single task. However, real world environments are dynamic, and thus require the ability to adapt to changes. By improving the design of the artificial neural network for learning tasks, we have come one step closer to artificial life.","abstract_html":"Supervised learning has long been used to modify the artificial neural network in order to perform classification tasks. However, the standard fully connected layered design is often inadequate when performing such tasks. We show that evolution can be used to design an artificial neural network that learns faster and more accurately. By evolving artificial neural networks within a dynamic environment, the artificial neural network is forced to use learning. This strategy combined with incremental evolution produces an artificial neural network that outperforms the standard fully-connected layered design. The resulting artificial neural network can learn to solve an entire domain of problems, including those of lesser complexity. Evolution alone can be used to create a network that solves a single task. However, real world environments are dynamic, and thus require the ability to adapt to changes. By improving the design of the artificial neural network for learning tasks, we have come one step closer to artificial life.","abstract_has_math":false,"creators":["Christenson, Christopher P."],"institution":"Texas State University-San Marcos","degree_name":"Master of Science","degree_level":"Masters","degree_discipline":"Computer Science","degree_department":null,"school":null,"contributors":[],"advisors":["Kaikhah, Khosrow"],"committee_chairs":[],"committee_members":[],"year":2004,"date_issued":"2004-12","date_published":"2004-12","updated_at":"2026-07-27T21:22:51Z","subjects":["neural networks","artificial intelligence"],"languages":["en"],"rights":[],"rights_urls":[],"identifier_entries":[]},"links":{"outbound_url":"https://hdl.handle.net/10877/9559","outbound_label":"Handle","outbound_source":"dc:identifier.uri"},"metadata_groups":[{"id":"people","label":"People","entries":[{"key":"dc:contributor.advisor","label":"Advisor","values":["Kaikhah, Khosrow"]},{"key":"dc:creator","label":"Author","values":["Christenson, Christopher P."]}]},{"id":"academic_context","label":"Academic Context","entries":[{"key":"dc:date.accessioned","label":"Dc Date Accessioned","values":["2020-04-01T13:55:31Z"]},{"key":"dc:date.available","label":"Dc Date Available","values":["2020-04-01T13:55:31Z"]},{"key":"dc:date.issued","label":"Date","values":["2004-12"]},{"key":"dc:type","label":"Dc Type","values":["Thesis"]},{"key":"thesis:degree_discipline","label":"Discipline","values":["Computer Science"]},{"key":"thesis:degree_level","label":"Degree Level","values":["Masters"]},{"key":"thesis:degree_name","label":"Degree Name","values":["Master of Science"]},{"key":"thesis:institution_name","label":"Thesis Institution Name","values":["Texas State University-San Marcos"]}]},{"id":"subjects_keywords","label":"Subjects and Keywords","entries":[{"key":"dc:subject","label":"Dc Subject","values":["neural networks","artificial intelligence"]}]},{"id":"language_rights","label":"Language and Rights","entries":[{"key":"dc:language.iso","label":"Language (ISO)","values":["en"]}]},{"id":"identifiers","label":"Identifiers","entries":[{"key":"dc:identifier.uri","label":"Identifier URI","values":["https://hdl.handle.net/10877/9559"]}]},{"id":"additional","label":"Additional Metadata","entries":[{"key":"dc:description.abstract","label":"Abstract","values":["Supervised learning has long been used to modify the artificial neural network in order to perform classification tasks. However, the standard fully connected layered design is often inadequate when performing such tasks. We show that evolution can be used to design an artificial neural network that learns faster and more accurately. By evolving artificial neural networks within a dynamic environment, the artificial neural network is forced to use learning. This strategy combined with incremental evolution produces an artificial neural network that outperforms the standard fully-connected layered design. The resulting artificial neural network can learn to solve an entire domain of problems, including those of lesser complexity. Evolution alone can be used to create a network that solves a single task. However, real world environments are dynamic, and thus require the ability to adapt to changes. By improving the design of the artificial neural network for learning tasks, we have come one step closer to artificial life."]},{"key":"dc:format","label":"Dc Format","values":["Text"]},{"key":"dc:format.medium","label":"Dc Format Medium","values":["1 file (.pdf)"]},{"key":"dc:title","label":"Title","values":["Evolving Learning Neural Networks"]}]}],"canonical_facts":{"dc:contributor.advisor":["Kaikhah, Khosrow"],"dc:creator":["Christenson, Christopher P."],"dc:date.accessioned":["2020-04-01T13:55:31Z"],"dc:date.available":["2020-04-01T13:55:31Z"],"dc:date.issued":["2004-12"],"dc:description.abstract":["Supervised learning has long been used to modify the artificial neural network in order to perform classification tasks. However, the standard fully connected layered design is often inadequate when performing such tasks. We show that evolution can be used to design an artificial neural network that learns faster and more accurately. By evolving artificial neural networks within a dynamic environment, the artificial neural network is forced to use learning. This strategy combined with incremental evolution produces an artificial neural network that outperforms the standard fully-connected layered design. The resulting artificial neural network can learn to solve an entire domain of problems, including those of lesser complexity. Evolution alone can be used to create a network that solves a single task. However, real world environments are dynamic, and thus require the ability to adapt to changes. By improving the design of the artificial neural network for learning tasks, we have come one step closer to artificial life."],"dc:format":["Text"],"dc:format.medium":["1 file (.pdf)"],"dc:identifier.uri":["https://hdl.handle.net/10877/9559"],"dc:language.iso":["en"],"dc:subject":["neural networks","artificial intelligence"],"dc:title":["Evolving Learning Neural Networks"],"dc:type":["Thesis"],"thesis:degree_discipline":["Computer Science"],"thesis:degree_level":["Masters"],"thesis:degree_name":["Master of Science"],"thesis:institution_name":["Texas State University-San Marcos"]},"updated_at":"2026-07-27T21:22:51Z"}