Grounding Language Learning in Vision for Artificial Intelligence and Brain Research
dc.contributor.author | Zhang, Yizhen | |
dc.date.accessioned | 2021-09-24T19:15:17Z | |
dc.date.available | 2023-09-01 | |
dc.date.available | 2021-09-24T19:15:17Z | |
dc.date.issued | 2021 | |
dc.identifier.uri | https://hdl.handle.net/2027.42/169841 | |
dc.description.abstract | Most models for natural language processing learn words merely from texts. However, humans learn language by referring to real-world experience and knowledge. My research aims to ground language learning in visual perception, taking one step closer to making machines learn language like humans. To achieve this goal, I have designed a two-stream model with deep neural networks. One stream extracts image features. The other stream extracts language features. The two streams merge to connect image and language features in a joint representation space. By contrastive learning, I have first trained the model to align images with their captions, and then refined the model to retrieve visual objects with language queries and infer their visual relations. After training, the model’s language stream is a stand-alone system capable of embedding words in a visually grounded semantic space. This space manifests principal dimensions explainable with human intuition and neurobiological knowledge. The visually grounded language model also enables compositional language understanding based on visual knowledge and multimodal image search with queries based on image-text combination. This model can also explain human brain activity observed with functional magnetic resonance imaging during natural language comprehension. It sheds new light on how the brain stores concepts and organizes concepts by their semantic relations and attributes. | |
dc.language.iso | en_US | |
dc.subject | Machine learning and artificial intelligence | |
dc.subject | Language learning | |
dc.subject | Visual grounding | |
dc.subject | Multimodal learning | |
dc.subject | Neuroscience | |
dc.subject | Grounded cognition | |
dc.title | Grounding Language Learning in Vision for Artificial Intelligence and Brain Research | |
dc.type | Thesis | |
dc.description.thesisdegreename | PhD | en_US |
dc.description.thesisdegreediscipline | Electrical and Computer Engineering | |
dc.description.thesisdegreegrantor | University of Michigan, Horace H. Rackham School of Graduate Studies | |
dc.contributor.committeemember | Liu, Zhongming | |
dc.contributor.committeemember | Brang, David Joseph | |
dc.contributor.committeemember | Fessler, Jeffrey A | |
dc.contributor.committeemember | Owens, Andrew | |
dc.subject.hlbsecondlevel | Electrical Engineering | |
dc.subject.hlbtoplevel | Engineering | |
dc.description.bitstreamurl | http://deepblue.lib.umich.edu/bitstream/2027.42/169841/1/zhyz_1.pdf | |
dc.identifier.doi | https://dx.doi.org/10.7302/2886 | |
dc.identifier.orcid | 0000-0002-2836-2666 | |
dc.identifier.name-orcid | Zhang, Yizhen; 0000-0002-2836-2666 | en_US |
dc.working.doi | 10.7302/2886 | en |
dc.owningcollname | Dissertations and Theses (Ph.D. and Master's) |
Files in this item
Remediation of Harmful Language
The University of Michigan Library aims to describe library materials in a way that respects the people and communities who create, use, and are represented in our collections. Report harmful or offensive language in catalog records, finding aids, or elsewhere in our collections anonymously through our metadata feedback form. More information at Remediation of Harmful Language.
Accessibility
If you are unable to use this file in its current format, please select the Contact Us link and we can modify it to make it more accessible to you.