{"id":{"repo_id":"nps","oai_identifier":"oai:calhoun.nps.edu:10945/72020"},"canonical_url":"https://search.dev.ndltd.org/etd/nps/oai:calhoun.nps.edu:10945/72020","repository":{"repo_id":"nps","name":"Naval Postgraduate School","base_url":"https://calhoun.nps.edu/server/oai/request"},"display":{"title":"FEDERATED LEARNING OF BAYESIAN NEURAL NETWORKS","abstract":"Although federated learning and Bayesian neural networks have been researched, there are few implementations of the federated learning of Bayesian networks. In this thesis, a federated learning training environment for Bayesian neural networks using a public code base, Flower, is developed. With it is the exploration of state-of-the-art architecture, residual networks, and Bayesian versions of it. These architectures are then tested with independently and identically distributed (IID) datasets and non-IID datasets derived from the Dirichlet distribution. Results show that the MC Dropout version of Bayesian neural networks can achieve state-of-the-art results—91% accuracy—for IID partitions of the CIFAR10 dataset through federated learning. When the partitions are non-IID, federated learning through inverse variance aggregation of probabilistic weights does as well as its deterministic counterpart, with roughly 83% accuracy. This shows that Bayesian neural networks can be federated and achieve state-of-the-art results as well.","abstract_html":"Although federated learning and Bayesian neural networks have been researched, there are few implementations of the federated learning of Bayesian networks. In this thesis, a federated learning training environment for Bayesian neural networks using a public code base, Flower, is developed. With it is the exploration of state-of-the-art architecture, residual networks, and Bayesian versions of it. These architectures are then tested with independently and identically distributed (IID) datasets and non-IID datasets derived from the Dirichlet distribution. Results show that the MC Dropout version of Bayesian neural networks can achieve state-of-the-art results—91% accuracy—for IID partitions of the CIFAR10 dataset through federated learning. When the partitions are non-IID, federated learning through inverse variance aggregation of probabilistic weights does as well as its deterministic counterpart, with roughly 83% accuracy. This shows that Bayesian neural networks can be federated and achieve state-of-the-art results as well.","abstract_has_math":false,"creators":["Loomis, Justin M."],"institution":"Monterey, CA; Naval Postgraduate School","degree_name":null,"degree_level":null,"degree_discipline":null,"degree_department":"Computer Science (CS)","school":null,"contributors":[],"advisors":["Orescanin, Marko"],"committee_chairs":[],"committee_members":[],"year":2023,"date_issued":"2023-03","date_published":"2023-03","updated_at":"2026-07-27T20:26:27Z","subjects":[],"languages":[],"rights":["This publication is a work of the U.S. Government as defined in Title 17, United States Code, Section 101. Copyright protection is not available for this work in the United States."],"rights_urls":[],"identifier_entries":[]},"links":{"outbound_url":"https://hdl.handle.net/10945/72020","outbound_label":"Handle","outbound_source":"dc:identifier.uri"},"metadata_groups":[{"id":"people","label":"People","entries":[{"key":"dc:contributor.advisor","label":"Advisor","values":["Orescanin, Marko"]},{"key":"dc:contributor.department","label":"Department","values":["Computer Science (CS)"]},{"key":"dc:creator","label":"Author","values":["Loomis, Justin M."]}]},{"id":"academic_context","label":"Academic Context","entries":[{"key":"dc:date.accessioned","label":"Dc Date Accessioned","values":["2023-05-03T16:03:17Z"]},{"key":"dc:date.available","label":"Dc Date Available","values":["2023-05-03T16:03:17Z"]},{"key":"dc:date.issued","label":"Date","values":["2023-03"]},{"key":"dc:publisher","label":"Institution","values":["Monterey, CA; Naval Postgraduate School"]},{"key":"dc:type","label":"Dc Type","values":["Thesis"]}]},{"id":"language_rights","label":"Language and Rights","entries":[{"key":"dc:rights","label":"Dc Rights","values":["This publication is a work of the U.S. Government as defined in Title 17, United States Code, Section 101. Copyright protection is not available for this work in the United States."]}]},{"id":"identifiers","label":"Identifiers","entries":[{"key":"dc:identifier.uri","label":"Identifier URI","values":["https://hdl.handle.net/10945/72020"]}]},{"id":"additional","label":"Additional Metadata","entries":[{"key":"dc:description.abstract","label":"Abstract","values":["Although federated learning and Bayesian neural networks have been researched, there are few implementations of the federated learning of Bayesian networks. In this thesis, a federated learning training environment for Bayesian neural networks using a public code base, Flower, is developed. With it is the exploration of state-of-the-art architecture, residual networks, and Bayesian versions of it. These architectures are then tested with independently and identically distributed (IID) datasets and non-IID datasets derived from the Dirichlet distribution. Results show that the MC Dropout version of Bayesian neural networks can achieve state-of-the-art results—91% accuracy—for IID partitions of the CIFAR10 dataset through federated learning. When the partitions are non-IID, federated learning through inverse variance aggregation of probabilistic weights does as well as its deterministic counterpart, with roughly 83% accuracy. This shows that Bayesian neural networks can be federated and achieve state-of-the-art results as well."]},{"key":"dc:title","label":"Title","values":["FEDERATED LEARNING OF BAYESIAN NEURAL NETWORKS"]}]}],"canonical_facts":{"dc:contributor.advisor":["Orescanin, Marko"],"dc:contributor.department":["Computer Science (CS)"],"dc:creator":["Loomis, Justin M."],"dc:date.accessioned":["2023-05-03T16:03:17Z"],"dc:date.available":["2023-05-03T16:03:17Z"],"dc:date.issued":["2023-03"],"dc:description.abstract":["Although federated learning and Bayesian neural networks have been researched, there are few implementations of the federated learning of Bayesian networks. In this thesis, a federated learning training environment for Bayesian neural networks using a public code base, Flower, is developed. With it is the exploration of state-of-the-art architecture, residual networks, and Bayesian versions of it. These architectures are then tested with independently and identically distributed (IID) datasets and non-IID datasets derived from the Dirichlet distribution. Results show that the MC Dropout version of Bayesian neural networks can achieve state-of-the-art results—91% accuracy—for IID partitions of the CIFAR10 dataset through federated learning. When the partitions are non-IID, federated learning through inverse variance aggregation of probabilistic weights does as well as its deterministic counterpart, with roughly 83% accuracy. This shows that Bayesian neural networks can be federated and achieve state-of-the-art results as well."],"dc:identifier.uri":["https://hdl.handle.net/10945/72020"],"dc:publisher":["Monterey, CA; Naval Postgraduate School"],"dc:rights":["This publication is a work of the U.S. Government as defined in Title 17, United States Code, Section 101. Copyright protection is not available for this work in the United States."],"dc:title":["FEDERATED LEARNING OF BAYESIAN NEURAL NETWORKS"],"dc:type":["Thesis"]},"updated_at":"2026-07-27T20:26:27Z"}