{"id":{"repo_id":"rowan","oai_identifier":"oai:rdw.rowan.edu:etd-3575"},"canonical_url":"https://search.ndltd.org/etd/rowan/oai:rdw.rowan.edu:etd-3575","repository":{"repo_id":"rowan","name":"Rowan University","base_url":"https://rdw.rowan.edu/do/oai/"},"display":{"title":"An investigation of the cortical learning algorithm","abstract":"Pattern recognition and machine learning fields have revolutionized countless industries and applications from biometric security to modern industrial assembly lines. The fields continue to accelerate as faster, more efficient processing hardware becomes commercially available. Despite the accelerated growth of the pattern recognition and machine learning fields, computers still are unable to learn, reason, and perform rudimentary tasks that humans and animals find routine. Animals are able to move fluidly, understand their environment, and maximize their chances of survival through adaptation - animals demonstrate intelligence. A primary argument in this thesis that we have not yet achieved a level of intelligence similar to humans and animals in the pattern recognition and machine learning fields, not due to a lack of computational power but, rather, due to lack of understanding of how the cortical structures of mammalian brain interact and operate. This thesis describes a cortical learning algorithm (CLA) that models how the cortical structures in the mammalian neocortex operate. Furthermore, a high level understanding of how the cortical structures in the mammalian brain interact, store semantic patterns, and auto-recall these patterns for future predictions are discussed. Finally, we demonstrate that the algorithm can build and maintain a model of its environment and provide feedback for actions and/or classification in a similar fashion to our understanding of cortical operation.","abstract_html":"Pattern recognition and machine learning fields have revolutionized countless industries and applications from biometric security to modern industrial assembly lines. The fields continue to accelerate as faster, more efficient processing hardware becomes commercially available. Despite the accelerated growth of the pattern recognition and machine learning fields, computers still are unable to learn, reason, and perform rudimentary tasks that humans and animals find routine. Animals are able to move fluidly, understand their environment, and maximize their chances of survival through adaptation - animals demonstrate intelligence. A primary argument in this thesis that we have not yet achieved a level of intelligence similar to humans and animals in the pattern recognition and machine learning fields, not due to a lack of computational power but, rather, due to lack of understanding of how the cortical structures of mammalian brain interact and operate. This thesis describes a cortical learning algorithm (CLA) that models how the cortical structures in the mammalian neocortex operate. Furthermore, a high level understanding of how the cortical structures in the mammalian brain interact, store semantic patterns, and auto-recall these patterns for future predictions are discussed. Finally, we demonstrate that the algorithm can build and maintain a model of its environment and provide feedback for actions and/or classification in a similar fashion to our understanding of cortical operation.","abstract_has_math":false,"creators":["Samaritano, Anthony C."],"institution":null,"degree_name":"MS Electrical and Computer Engineering","degree_level":"Thesis","degree_discipline":"Electrical & Computer Engineering","degree_department":null,"school":null,"contributors":["Polikar, Robi","Bouaynaya, Nidhal","Baliga, Ganesh"],"advisors":[],"committee_chairs":[],"committee_members":[],"year":null,"date_issued":"","date_published":null,"updated_at":"2026-11-19T08:58:51Z","subjects":["algorithms","cortical learning algorithm","hierarchical temporal memory","machine learning","neural network","neuroscience","Artificial intelligence","Neocortex","Electrical and Computer Engineering","Neuroscience and Neurobiology"],"languages":[],"rights":[],"rights_urls":[],"identifier_entries":[],"person_identifier_entries":[]},"links":{"outbound_url":"https://rdw.rowan.edu/etd/2572","outbound_label":"Repository record","outbound_source":"dc:identifier","record_url":"https://rdw.rowan.edu/etd/2572","record_label":"Repository record","record_kind":"record","record_source":"dc:identifier","download_url":null,"download_label":null,"download_source":null,"access_status":null,"embargo_until":null,"access_note":null},"source_record":{"url":"https://rdw.rowan.edu/do/oai/?verb=GetRecord&metadataPrefix=oai_etdms&identifier=oai%3Ardw.rowan.edu%3Aetd-3575","prefix":"oai_etdms"},"metadata_groups":[{"id":"people","label":"People","entries":[{"key":"dc:contributor","label":"Contributor","values":["Polikar, Robi","Bouaynaya, Nidhal","Baliga, Ganesh"]},{"key":"dc:creator","label":"Author","values":["Samaritano, Anthony C."]}]},{"id":"academic_context","label":"Academic Context","entries":[{"key":"dc:date.available","label":"Dc Date Available","values":["2018-06-01T07:00:00Z"]},{"key":"dc:date.created","label":"Dc Date Created","values":["2018-05-24T07:00:00Z"]},{"key":"thesis:degree_discipline","label":"Discipline","values":["Electrical & Computer Engineering"]},{"key":"thesis:degree_level","label":"Degree Level","values":["Thesis"]},{"key":"thesis:degree_name","label":"Degree Name","values":["MS Electrical and Computer Engineering"]}]},{"id":"subjects_keywords","label":"Subjects and Keywords","entries":[{"key":"dc:subject","label":"Dc Subject","values":["algorithms","cortical learning algorithm","hierarchical temporal memory","machine learning","neural network","neuroscience","Artificial intelligence","Neocortex","Electrical and Computer Engineering","Neuroscience and Neurobiology"]}]},{"id":"identifiers","label":"Identifiers","entries":[{"key":"dc:identifier","label":"Identifier","values":["https://rdw.rowan.edu/etd/2572"]}]},{"id":"additional","label":"Additional Metadata","entries":[{"key":"dc:description.abstract","label":"Abstract","values":["Pattern recognition and machine learning fields have revolutionized countless industries and applications from biometric security to modern industrial assembly lines. The fields continue to accelerate as faster, more efficient processing hardware becomes commercially available. Despite the accelerated growth of the pattern recognition and machine learning fields, computers still are unable to learn, reason, and perform rudimentary tasks that humans and animals find routine. Animals are able to move fluidly, understand their environment, and maximize their chances of survival through adaptation - animals demonstrate intelligence. A primary argument in this thesis that we have not yet achieved a level of intelligence similar to humans and animals in the pattern recognition and machine learning fields, not due to a lack of computational power but, rather, due to lack of understanding of how the cortical structures of mammalian brain interact and operate. This thesis describes a cortical learning algorithm (CLA) that models how the cortical structures in the mammalian neocortex operate. Furthermore, a high level understanding of how the cortical structures in the mammalian brain interact, store semantic patterns, and auto-recall these patterns for future predictions are discussed. Finally, we demonstrate that the algorithm can build and maintain a model of its environment and provide feedback for actions and/or classification in a similar fashion to our understanding of cortical operation."]},{"key":"dc:title","label":"Title","values":["An investigation of the cortical learning algorithm"]}]}],"canonical_facts":{"dc:contributor":["Polikar, Robi","Bouaynaya, Nidhal","Baliga, Ganesh"],"dc:creator":["Samaritano, Anthony C."],"dc:date.available":["2018-06-01T07:00:00Z"],"dc:date.created":["2018-05-24T07:00:00Z"],"dc:description.abstract":["Pattern recognition and machine learning fields have revolutionized countless industries and applications from biometric security to modern industrial assembly lines. The fields continue to accelerate as faster, more efficient processing hardware becomes commercially available. Despite the accelerated growth of the pattern recognition and machine learning fields, computers still are unable to learn, reason, and perform rudimentary tasks that humans and animals find routine. Animals are able to move fluidly, understand their environment, and maximize their chances of survival through adaptation - animals demonstrate intelligence. A primary argument in this thesis that we have not yet achieved a level of intelligence similar to humans and animals in the pattern recognition and machine learning fields, not due to a lack of computational power but, rather, due to lack of understanding of how the cortical structures of mammalian brain interact and operate. This thesis describes a cortical learning algorithm (CLA) that models how the cortical structures in the mammalian neocortex operate. Furthermore, a high level understanding of how the cortical structures in the mammalian brain interact, store semantic patterns, and auto-recall these patterns for future predictions are discussed. Finally, we demonstrate that the algorithm can build and maintain a model of its environment and provide feedback for actions and/or classification in a similar fashion to our understanding of cortical operation."],"dc:identifier":["https://rdw.rowan.edu/etd/2572"],"dc:subject":["algorithms","cortical learning algorithm","hierarchical temporal memory","machine learning","neural network","neuroscience","Artificial intelligence","Neocortex","Electrical and Computer Engineering","Neuroscience and Neurobiology"],"dc:title":["An investigation of the cortical learning algorithm"],"thesis:degree_discipline":["Electrical & Computer Engineering"],"thesis:degree_level":["Thesis"],"thesis:degree_name":["MS Electrical and Computer Engineering"]},"updated_at":"2026-11-19T08:58:51Z"}