VGU RESEARCH REPOSITORY
Please use this identifier to cite or link to this item:
https://epub.vgu.edu.vn/handle/dlibvgu/1275
DC Field | Value | Language |
---|---|---|
dc.contributor.author | Lu Minh Khuong | en_US |
dc.date.accessioned | 2022-01-18T04:26:01Z | - |
dc.date.available | 2022-01-18T04:26:01Z | - |
dc.date.issued | 2021 | - |
dc.identifier.uri | http://epub.vgu.edu.vn/handle/dlibvgu/1275 | - |
dc.description.abstract | This thesis introduces a new approach of open set recognition that prevents catastrophic forgetting in deep continual learning. A single model combines a joint probabilistic encoder with a generative model and a linear classifier, all of which are shared among tasks that arrive in sequence. It is developed based on the Variational Auto Encoder (VAE) then wrap the encoder and decoder in a Wide Residual Network (Wide Res Net) to increase the model's accuracy | en_US |
dc.language.iso | en | en_US |
dc.subject | Deep continual learning | en_US |
dc.title | Open set recognition for deep continual learning | en_US |
dc.type | Thesis | en_US |
item.grantfulltext | restricted | - |
item.fulltext | With Fulltext | - |
item.languageiso639-1 | other | - |
Appears in Collections: | Computer Science (CS) |
Files in This Item:
File | Description | Size | Format | Existing users please Login |
---|---|---|---|---|
Open set recognition for deep continual learning.pdf | 6 MB | Adobe PDF |
Page view(s)
138
checked on May 2, 2024
Download(s)
81
checked on May 2, 2024
Google ScholarTM
Check
Items are protected by © Copyright of Vietnamese - German University Library