{"id":{"repo_id":"rowan","oai_identifier":"oai:rdw.rowan.edu:etd-4013"},"canonical_url":"https://search.ndltd.org/etd/rowan/oai:rdw.rowan.edu:etd-4013","repository":{"repo_id":"rowan","name":"Rowan University","base_url":"https://rdw.rowan.edu/do/oai/"},"display":{"title":"LOW MEMORY CONTINUAL LEARNING CLASSIFICATION ALGORITHMS FOR LOW RESOURCE HARDWARE","abstract":"Continual Learning (CL) is a machine learning approach which focuses on continuous learning of data rather than single dataset-based learning. In this thesis, this same focus is applied with respect to the field of machine learning for embedded devices which is still in the early stages of development. This focus is further used to develop various algorithms such as utilizing prior trained starting networks, weighted output schemes, and replay or reduced datasets for training while maintaining a consistent focus on low resource devices to maintain acceptable performance. The experimental results show an improvement in model training times as compared to the time to train a neural network using all available information with the following accuracy for the Fashion MNIST dataset (~90% to 73% accuracy on 10 classes with a factor of 10 reduction in training time). The other main result showed a reduction in required memory as only 1 class size worth of data is required to be stored at a time rather than the full dataset for non-Replay algorithms. For the Replay based algorithms, this is still reduced to less than 2 classes worth of data for 10 classes which is an 80% reduction overall in memory. This was done with the goal of creating a usable model while a fully trained network is developed on backend systems to limit overall downtime and still maintain system performance.","abstract_html":"Continual Learning (CL) is a machine learning approach which focuses on continuous learning of data rather than single dataset-based learning. In this thesis, this same focus is applied with respect to the field of machine learning for embedded devices which is still in the early stages of development. This focus is further used to develop various algorithms such as utilizing prior trained starting networks, weighted output schemes, and replay or reduced datasets for training while maintaining a consistent focus on low resource devices to maintain acceptable performance. The experimental results show an improvement in model training times as compared to the time to train a neural network using all available information with the following accuracy for the Fashion MNIST dataset (~90% to 73% accuracy on 10 classes with a factor of 10 reduction in training time). The other main result showed a reduction in required memory as only 1 class size worth of data is required to be stored at a time rather than the full dataset for non-Replay algorithms. For the Replay based algorithms, this is still reduced to less than 2 classes worth of data for 10 classes which is an 80% reduction overall in memory. This was done with the goal of creating a usable model while a fully trained network is developed on backend systems to limit overall downtime and still maintain system performance.","abstract_has_math":false,"creators":["Chadwick, Autumn Lilly"],"institution":null,"degree_name":"M.S. Computer Science","degree_level":"Thesis","degree_discipline":"Computer Science","degree_department":null,"school":null,"contributors":["Shen-Shyang Ho","Anthony Breitzman, Ph.D.","Ning Wang, Ph.D."],"advisors":[],"committee_chairs":[],"committee_members":[],"year":null,"date_issued":"","date_published":null,"updated_at":"2026-11-19T08:59:24Z","subjects":["Continual Learning","Embedded Devices","Machine learning","Computer Sciences"],"languages":[],"rights":[],"rights_urls":[],"identifier_entries":[],"person_identifier_entries":[]},"links":{"outbound_url":"https://rdw.rowan.edu/etd/3012","outbound_label":"Repository record","outbound_source":"dc:identifier","record_url":"https://rdw.rowan.edu/etd/3012","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-4013","prefix":"oai_etdms"},"metadata_groups":[{"id":"people","label":"People","entries":[{"key":"dc:contributor","label":"Contributor","values":["Shen-Shyang Ho","Anthony Breitzman, Ph.D.","Ning Wang, Ph.D."]},{"key":"dc:creator","label":"Author","values":["Chadwick, Autumn Lilly"]}]},{"id":"academic_context","label":"Academic Context","entries":[{"key":"dc:date.available","label":"Dc Date Available","values":["2022-05-25T07:00:00Z"]},{"key":"dc:date.created","label":"Dc Date Created","values":["2022-05-23T07:00:00Z"]},{"key":"thesis:degree_discipline","label":"Discipline","values":["Computer Science"]},{"key":"thesis:degree_level","label":"Degree Level","values":["Thesis"]},{"key":"thesis:degree_name","label":"Degree Name","values":["M.S. Computer Science"]}]},{"id":"subjects_keywords","label":"Subjects and Keywords","entries":[{"key":"dc:subject","label":"Dc Subject","values":["Continual Learning","Embedded Devices","Machine learning","Computer Sciences"]}]},{"id":"identifiers","label":"Identifiers","entries":[{"key":"dc:identifier","label":"Identifier","values":["https://rdw.rowan.edu/etd/3012"]}]},{"id":"additional","label":"Additional Metadata","entries":[{"key":"dc:description.abstract","label":"Abstract","values":["Continual Learning (CL) is a machine learning approach which focuses on continuous learning of data rather than single dataset-based learning. In this thesis, this same focus is applied with respect to the field of machine learning for embedded devices which is still in the early stages of development. This focus is further used to develop various algorithms such as utilizing prior trained starting networks, weighted output schemes, and replay or reduced datasets for training while maintaining a consistent focus on low resource devices to maintain acceptable performance. The experimental results show an improvement in model training times as compared to the time to train a neural network using all available information with the following accuracy for the Fashion MNIST dataset (~90% to 73% accuracy on 10 classes with a factor of 10 reduction in training time). The other main result showed a reduction in required memory as only 1 class size worth of data is required to be stored at a time rather than the full dataset for non-Replay algorithms. For the Replay based algorithms, this is still reduced to less than 2 classes worth of data for 10 classes which is an 80% reduction overall in memory. This was done with the goal of creating a usable model while a fully trained network is developed on backend systems to limit overall downtime and still maintain system performance."]},{"key":"dc:title","label":"Title","values":["LOW MEMORY CONTINUAL LEARNING CLASSIFICATION ALGORITHMS FOR LOW RESOURCE HARDWARE"]}]}],"canonical_facts":{"dc:contributor":["Shen-Shyang Ho","Anthony Breitzman, Ph.D.","Ning Wang, Ph.D."],"dc:creator":["Chadwick, Autumn Lilly"],"dc:date.available":["2022-05-25T07:00:00Z"],"dc:date.created":["2022-05-23T07:00:00Z"],"dc:description.abstract":["Continual Learning (CL) is a machine learning approach which focuses on continuous learning of data rather than single dataset-based learning. In this thesis, this same focus is applied with respect to the field of machine learning for embedded devices which is still in the early stages of development. This focus is further used to develop various algorithms such as utilizing prior trained starting networks, weighted output schemes, and replay or reduced datasets for training while maintaining a consistent focus on low resource devices to maintain acceptable performance. The experimental results show an improvement in model training times as compared to the time to train a neural network using all available information with the following accuracy for the Fashion MNIST dataset (~90% to 73% accuracy on 10 classes with a factor of 10 reduction in training time). The other main result showed a reduction in required memory as only 1 class size worth of data is required to be stored at a time rather than the full dataset for non-Replay algorithms. For the Replay based algorithms, this is still reduced to less than 2 classes worth of data for 10 classes which is an 80% reduction overall in memory. This was done with the goal of creating a usable model while a fully trained network is developed on backend systems to limit overall downtime and still maintain system performance."],"dc:identifier":["https://rdw.rowan.edu/etd/3012"],"dc:subject":["Continual Learning","Embedded Devices","Machine learning","Computer Sciences"],"dc:title":["LOW MEMORY CONTINUAL LEARNING CLASSIFICATION ALGORITHMS FOR LOW RESOURCE HARDWARE"],"thesis:degree_discipline":["Computer Science"],"thesis:degree_level":["Thesis"],"thesis:degree_name":["M.S. Computer Science"]},"updated_at":"2026-11-19T08:59:24Z"}