Using mutual information to evaluate the generalization capability of deep learning neural networks
There is a need to better understand how generalization works in a deep learning model. The goal of this paper is to provide a clearer view of the black box called neural network. This is done by using information theory to compute the flow of information within a network. The proposed framework use...
Saved in:
主要作者: | Kan, Shawn Jung Tze |
---|---|
其他作者: | Althea Liang |
格式: | Final Year Project |
語言: | English |
出版: |
Nanyang Technological University
2020
|
主題: | |
在線閱讀: | https://hdl.handle.net/10356/137910 |
標簽: |
添加標簽
沒有標簽, 成為第一個標記此記錄!
|
相似書籍
-
Deep learning-based concrete image analysis and generalization capability
由: Qian, Hanjie
出版: (2024) -
Learning capabilities of neural networks
由: Huang, Guangbin.
出版: (2008) -
Evaluating and optimizing neural network models with neuromorphic capable and non-capable hardware
由: Cheong, Gordon Chin Loong
出版: (2021) -
Online deep learning: Learning deep neural networks on the fly
由: SAHOO, Doyen, et al.
出版: (2018) -
Evaluation and comparison of various deep neural networks for monocular depth estimation
由: Zhang, Ziyi
出版: (2020)