Towards understanding residual neural networks
Thesis: M. Eng., Massachusetts Institute of Technology, Department of Electrical Engineering and Computer Science, 2019
| Autor principal: | |
|---|---|
| Otros Autores: | |
| Formato: | Tesis |
| Lenguaje: | eng |
| Publicado: |
Massachusetts Institute of Technology
2019
|
| Materias: | |
| Acceso en línea: | https://hdl.handle.net/1721.1/123067 |
| _version_ | 1826206279996014592 |
|---|---|
| author | Zeng, Brandon. |
| author2 | Aleksander Ma̧dry. |
| author_facet | Aleksander Ma̧dry. Zeng, Brandon. |
| author_sort | Zeng, Brandon. |
| collection | MIT |
| description | Thesis: M. Eng., Massachusetts Institute of Technology, Department of Electrical Engineering and Computer Science, 2019 |
| first_indexed | 2024-09-23T13:26:57Z |
| format | Thesis |
| id | mit-1721.1/123067 |
| institution | Massachusetts Institute of Technology |
| language | eng |
| last_indexed | 2024-09-23T13:26:57Z |
| publishDate | 2019 |
| publisher | Massachusetts Institute of Technology |
| record_format | dspace |
| spelling | mit-1721.1/1230672019-11-22T03:17:44Z Towards understanding residual neural networks Zeng, Brandon. Aleksander Ma̧dry. Massachusetts Institute of Technology. Department of Electrical Engineering and Computer Science. Massachusetts Institute of Technology. Department of Electrical Engineering and Computer Science Electrical Engineering and Computer Science. Thesis: M. Eng., Massachusetts Institute of Technology, Department of Electrical Engineering and Computer Science, 2019 Cataloged from PDF version of thesis. Includes bibliographical references (page 37). Residual networks (ResNets) are now a prominent architecture in the field of deep learning. However, an explanation for their success remains elusive. The original view is that residual connections allows for the training of deeper networks, but it is not clear that added layers are always useful, or even how they are used. In this work, we find that residual connections distribute learning behavior across layers, allowing resnets to indeed effectively use deeper layers and outperform standard networks. We support this explanation with results for network gradients and representation learning that show that residual connections make the training of individual residual blocks easier. by Brandon Zeng. M. Eng. M.Eng. Massachusetts Institute of Technology, Department of Electrical Engineering and Computer Science 2019-11-22T00:09:30Z 2019-11-22T00:09:30Z 2019 2019 Thesis https://hdl.handle.net/1721.1/123067 1127292128 eng MIT theses are protected by copyright. They may be viewed, downloaded, or printed from this source but further reproduction or distribution in any format is prohibited without written permission. http://dspace.mit.edu/handle/1721.1/7582 37 pages application/pdf Massachusetts Institute of Technology |
| spellingShingle | Electrical Engineering and Computer Science. Zeng, Brandon. Towards understanding residual neural networks |
| title | Towards understanding residual neural networks |
| title_full | Towards understanding residual neural networks |
| title_fullStr | Towards understanding residual neural networks |
| title_full_unstemmed | Towards understanding residual neural networks |
| title_short | Towards understanding residual neural networks |
| title_sort | towards understanding residual neural networks |
| topic | Electrical Engineering and Computer Science. |
| url | https://hdl.handle.net/1721.1/123067 |
| work_keys_str_mv | AT zengbrandon towardsunderstandingresidualneuralnetworks |