{"id":{"repo_id":"njit","oai_identifier":"oai:digitalcommons.njit.edu:theses-1039"},"canonical_url":"https://search.dev.ndltd.org/etd/njit/oai:digitalcommons.njit.edu:theses-1039","repository":{"repo_id":"njit","name":"NJIT","base_url":"https://digitalcommons.njit.edu/do/oai/"},"display":{"title":"Characteristics of different deep neural networks and application of pre-trained model without transfer learning","abstract":"Deep neural networks have been successful in many areas, some of them even surpass human performances. The goal of this thesis is using data simulations to present different characteristics of three deep neural networks: fully connected deep neural network, convolutional neural network, recurrent neural network, which will perform best when dealing with different feature patterns. By using these characteristics to design a deep neural network on top of an adopted pre-trained model with untrainable layers, achieved an averagely 11.1% improvement than a model with transfer learning method.","abstract_html":"Deep neural networks have been successful in many areas, some of them even surpass human performances. The goal of this thesis is using data simulations to present different characteristics of three deep neural networks: fully connected deep neural network, convolutional neural network, recurrent neural network, which will perform best when dealing with different feature patterns. By using these characteristics to design a deep neural network on top of an adopted pre-trained model with untrainable layers, achieved an averagely 11.1% improvement than a model with transfer learning method.","abstract_has_math":false,"creators":["Peng, Zhiqi"],"institution":null,"degree_name":"Master of Science in Computer Science - (M.S.)","degree_level":null,"degree_discipline":"Computer Science","degree_department":null,"school":null,"contributors":["Zhi Wei","Usman W. Roshan","Hai Nhat Phan"],"advisors":[],"committee_chairs":[],"committee_members":[],"year":2017,"date_issued":"2017-12-31T08:00:00Z","date_published":"2017-12-31T08:00:00Z","updated_at":"2026-07-24T03:22:07Z","subjects":["Deep neural networks","Data simulations","Computer Sciences"],"languages":[],"rights":[],"rights_urls":[],"identifier_entries":[]},"links":{"outbound_url":"https://digitalcommons.njit.edu/theses/40","outbound_label":"Repository record","outbound_source":"dc:identifier"},"metadata_groups":[{"id":"people","label":"People","entries":[{"key":"dc:contributor","label":"Contributor","values":["Zhi Wei","Usman W. Roshan","Hai Nhat Phan"]},{"key":"dc:creator","label":"Author","values":["Peng, Zhiqi"]}]},{"id":"academic_context","label":"Academic Context","entries":[{"key":"dc:type","label":"Dc Type","values":["Thesis"]},{"key":"thesis:degree_discipline","label":"Discipline","values":["Computer Science"]},{"key":"thesis:degree_name","label":"Degree Name","values":["Master of Science in Computer Science - (M.S.)"]}]},{"id":"subjects_keywords","label":"Subjects and Keywords","entries":[{"key":"dc:subject","label":"Dc Subject","values":["Deep neural networks","Data simulations","Computer Sciences"]}]},{"id":"identifiers","label":"Identifiers","entries":[{"key":"dc:identifier","label":"Identifier","values":["https://digitalcommons.njit.edu/theses/40"]}]},{"id":"additional","label":"Additional Metadata","entries":[{"key":"dc:description.abstract","label":"Abstract","values":["Deep neural networks have been successful in many areas, some of them even surpass human performances. The goal of this thesis is using data simulations to present different characteristics of three deep neural networks: fully connected deep neural network, convolutional neural network, recurrent neural network, which will perform best when dealing with different feature patterns. By using these characteristics to design a deep neural network on top of an adopted pre-trained model with untrainable layers, achieved an averagely 11.1% improvement than a model with transfer learning method."]},{"key":"dc:title","label":"Title","values":["Characteristics of different deep neural networks and application of pre-trained model without transfer learning"]}]}],"canonical_facts":{"dc:contributor":["Zhi Wei","Usman W. Roshan","Hai Nhat Phan"],"dc:creator":["Peng, Zhiqi"],"dc:description.abstract":["Deep neural networks have been successful in many areas, some of them even surpass human performances. The goal of this thesis is using data simulations to present different characteristics of three deep neural networks: fully connected deep neural network, convolutional neural network, recurrent neural network, which will perform best when dealing with different feature patterns. By using these characteristics to design a deep neural network on top of an adopted pre-trained model with untrainable layers, achieved an averagely 11.1% improvement than a model with transfer learning method."],"dc:identifier":["https://digitalcommons.njit.edu/theses/40"],"dc:subject":["Deep neural networks","Data simulations","Computer Sciences"],"dc:title":["Characteristics of different deep neural networks and application of pre-trained model without transfer learning"],"dc:type":["Thesis"],"thesis:degree_discipline":["Computer Science"],"thesis:degree_name":["Master of Science in Computer Science - (M.S.)"]},"updated_at":"2026-07-24T03:22:07Z"}