dc.contributor.advisor | Mortazavi, Bobak | |
dc.creator | Pakbin, Arash | |
dc.date.accessioned | 2021-04-30T22:13:59Z | |
dc.date.available | 2021-04-30T22:13:59Z | |
dc.date.created | 2020-12 | |
dc.date.issued | 2020-11-13 | |
dc.date.submitted | December 2020 | |
dc.identifier.uri | https://hdl.handle.net/1969.1/192839 | |
dc.description.abstract | Alpha-beta network is a mixture of deep neural networks, implementing a mixture of experts, where each component is a neural network. It is trained using the expectation-maximization algorithm. It enables context-awareness as each component is pushed to give context-specific predictions. Such structure enables context uncertainty quantification as well. The effectiveness of alpha-beta network was assessed using two real-world activity datasets: UCI OPPORTUNITY and an in-house dataset. The model has shown superior performance compared to the baselines. | en |
dc.format.mimetype | application/pdf | |
dc.language.iso | en | |
dc.subject | mixture of experts | en |
dc.subject | expectation maximization | en |
dc.subject | context awareness | en |
dc.subject | uncertainty quantification | en |
dc.title | Context-aware Mixture of Deep Neural Networks | en |
dc.type | Thesis | en |
thesis.degree.department | Computer Science and Engineering | en |
thesis.degree.discipline | Computer Science | en |
thesis.degree.grantor | Texas A&M University | en |
thesis.degree.name | Master of Science | en |
thesis.degree.level | Masters | en |
dc.contributor.committeeMember | Wang, Zhangyang (Atlas) | |
dc.contributor.committeeMember | Qian, Xiaoning | |
dc.type.material | text | en |
dc.date.updated | 2021-04-30T22:14:00Z | |
local.etdauthor.orcid | 0000-0002-0579-5725 | |