Towards more biologically plausible deep learning and visual processing
Thesis: S.M., Massachusetts Institute of Technology, Department of Electrical Engineering and Computer Science, 2017.
| Main Author: | |
|---|---|
| Other Authors: | |
| Format: | Thesis |
| Language: | eng |
| Published: |
Massachusetts Institute of Technology
2017
|
| Subjects: | |
| Online Access: | http://hdl.handle.net/1721.1/111920 |
| _version_ | 1826211434657218560 |
|---|---|
| author | Liao, Qianli |
| author2 | Tomaso A. Poggio. |
| author_facet | Tomaso A. Poggio. Liao, Qianli |
| author_sort | Liao, Qianli |
| collection | MIT |
| description | Thesis: S.M., Massachusetts Institute of Technology, Department of Electrical Engineering and Computer Science, 2017. |
| first_indexed | 2024-09-23T15:05:50Z |
| format | Thesis |
| id | mit-1721.1/111920 |
| institution | Massachusetts Institute of Technology |
| language | eng |
| last_indexed | 2024-09-23T15:05:50Z |
| publishDate | 2017 |
| publisher | Massachusetts Institute of Technology |
| record_format | dspace |
| spelling | mit-1721.1/1119202019-04-12T22:49:56Z Towards more biologically plausible deep learning and visual processing Liao, Qianli Tomaso A. Poggio. 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: S.M., Massachusetts Institute of Technology, Department of Electrical Engineering and Computer Science, 2017. Cataloged from PDF version of thesis. Includes bibliographical references (pages 85-91). Over the last decade, we have witnessed tremendous successes of Artificial Neural Networks (ANNs) on solving a wide range of Al tasks. However, there is considerably less development in understanding the biological neural networks in primate cortex. In this thesis, I try to bridge the gap between artificial and biological neural networks. I argue that it would be beneficial to build ANNs that are both biologically-plausible and well-performing, since they may serve as models for the brain and guide neuroscience research. On the other hand, developing a biology-compatible framework for ANNs makes it possible to borrow ideas from neuroscience to improve the performance of AI systems. I discuss several aspects of modern ANNs that can be made more consistent with biology: (1) the backpropagation learning algorithm (2) ultra-deep neural networks (e.g., ResNet, He et al., 2016) for visual processing (3) Batch Normalization (Ioffe and Szegedy, 2015). For each of the three aspects, I propose biologically-plausible modifications of the ANN models to make them more implementable by the brain while maintaining (or even improving) their performance. by Qianli Liao. S.M. 2017-10-18T15:10:04Z 2017-10-18T15:10:04Z 2017 2017 Thesis http://hdl.handle.net/1721.1/111920 1005706061 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 91 pages application/pdf Massachusetts Institute of Technology |
| spellingShingle | Electrical Engineering and Computer Science. Liao, Qianli Towards more biologically plausible deep learning and visual processing |
| title | Towards more biologically plausible deep learning and visual processing |
| title_full | Towards more biologically plausible deep learning and visual processing |
| title_fullStr | Towards more biologically plausible deep learning and visual processing |
| title_full_unstemmed | Towards more biologically plausible deep learning and visual processing |
| title_short | Towards more biologically plausible deep learning and visual processing |
| title_sort | towards more biologically plausible deep learning and visual processing |
| topic | Electrical Engineering and Computer Science. |
| url | http://hdl.handle.net/1721.1/111920 |
| work_keys_str_mv | AT liaoqianli towardsmorebiologicallyplausibledeeplearningandvisualprocessing |