Using mutual information to evaluate the generalization capability of deep learning neural networks

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:

書目詳細資料
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:	Engineering::Computer science and engineering::Information systems
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)

Deep learning neural network for image processing
由: Ma, Xueqing
出版: (2020)

Learn to navigate through deep neural networks
由: Wu, Keyu
出版: (2020)

Deep learning and computer chess (Part 1): using neural networks for chess evaluation functions
由: U, Jeremy Keat
出版: (2024)

Dynamically growing neural network architecture for lifelong deep learning on the edge
由: Piyasena, Duvindu, et al.
出版: (2021)

Auxiliary network design for local learning in deep neural networks
由: Peng, Jiawei
出版: (2021)

Improving neural relation extraction with implicit mutual relations
由: KUANG, Jun, et al.
出版: (2020)

Machine learning / deep learning approach to soundscape evaluations
由: Wong, Arthur Jun Xiang
出版: (2024)

Deep learning methods for diagnosis of epilepsy from EEG using convolutional neural networks
由: Du, Cuiqianhe
出版: (2018)

Deep learning neural networks for NAO robot control
由: Tee, Enid Mun Xin
出版: (2019)

JCBIE: a joint continual learning neural network for biomedical information extraction
由: He, Kai, et al.
出版: (2023)

Hybrid deep neural network and deep reinforcement learning for algorithmic finance
由: Ooi, Min Hui
出版: (2022)

Using deep neural networks for chess position evaluation
由: Phang, Benito Yan Feng
出版: (2023)

Deep neural networks for stock forecasting
由: Gao, Kexin
出版: (2022)

Attack on prediction confidence of deep learning neural networks
由: Ng, Garyl Xuan
出版: (2022)

Stock trading and prediction using deep learning neural network
由: Cheam, Nicholas Yen Kait
出版: (2018)

Improving the generalization capability of face spoofing detection
由: Li, Haoliang
出版: (2018)

Robust deep learning on graphs using neural PDEs
由: Gui, Pengzhe
出版: (2023)

Stock trading & prediction using deep learning neural networks
由: Gowri, Kannan
出版: (2017)

Multiagent reinforcement learning with graphical mutual information maximization
由: Ding, Shifei, et al.
出版: (2023)

Learning strategies for physics-informed neural networks
由: Wong, Jian Cheng
出版: (2025)

Motive imagery scoring based on deep neural network
由: Yu, Sicheng
出版: (2019)

Coronary artery lumen segmentation by deep learning neural networks
由: Huang, Lu
出版: (2018)

Evaluation of backdoor attacks and defenses to deep neural networks
由: Ooi, Ying Xuan
出版: (2024)

Towards theoretically understanding why SGD generalizes better than ADAM in deep learning
由: ZHOU, Pan, et al.
出版: (2020)

Speeding up deep neural network training with decoupled and analytic learning
由: Zhuang, Huiping
出版: (2021)

Online and continual learning using randomization based deep neural networks
由: Sreenivasan, Shiva
出版: (2023)

Stock trading prediction using deep learning neural networks
由: Ong, Hao Cong
出版: (2021)

Intelligent air handler incorporating neural network control capability
由: Arifin Purba Sigumonrong.
出版: (2008)

Exploring low complexity embedded architectures for deep neural networks
由: Chatterjee, Soham
出版: (2021)

Deep GRU neural networks for Apple stock price prediction
由: Ji, YiJun
出版: (2023)

Flexible job-shop scheduling via graph neural network and deep reinforcement learning
由: SONG, Wen, et al.
出版: (2023)

IMPROVED GRADIENT-BASED LEARNING FOR ENHANCED EFFICIENCY AND GENERALIZATION OF DEEP NEURAL NETWORKS
由: DU JIAWEI
出版: (2023)

Implementation of generalized mutual exclusion constraints using critical places and marking estimation
由: Yang, Benyuan, et al.
出版: (2022)

Evaluation of semi-supervised classification algorithms with deep contextualizes document representations
由: Yong, Hao
出版: (2021)

A hybrid approach for partial discharge classification: combining traditional machine learning and deep neural network
由: Ding, Shaobo
出版: (2023)