Visualizing interpretations of deep neural networks

Deep neural networks are notoriously black boxes that defy human interpretations. The lack of understanding of the decision process of neural networks erode public trust and prevent wide application of AI. In this project, we will develop a set of tools that visualize interpretations of deep neural...

Full description

Saved in:

Bibliographic Details
Main Author:	Tan, Ryan Kang Wei
Other Authors:	Li Boyang
Format:	Final Year Project
Language:	English
Published:	Nanyang Technological University 2022
Subjects:	Engineering::Computer science and engineering
Online Access:	https://hdl.handle.net/10356/162869
Tags:	Add Tag No Tags, Be the first to tag this record!
Institution:	Nanyang Technological University
Language:	English

id	sg-ntu-dr.10356-162869
record_format	dspace
spelling	sg-ntu-dr.10356-1628692022-11-11T06:26:22Z Visualizing interpretations of deep neural networks Tan, Ryan Kang Wei Li Boyang School of Computer Science and Engineering boyang.li@ntu.edu.sg Engineering::Computer science and engineering Deep neural networks are notoriously black boxes that defy human interpretations. The lack of understanding of the decision process of neural networks erode public trust and prevent wide application of AI. In this project, we will develop a set of tools that visualize interpretations of deep neural networks, so that the general public can intuitively understand how these networks make decisions. For example, for a given prediction made by the network, we can visualize how data points in the training set affect the prediction. Bachelor of Engineering (Computer Science) 2022-11-11T06:26:22Z 2022-11-11T06:26:22Z 2022 Final Year Project (FYP) Tan, R. K. W. (2022). Visualizing interpretations of deep neural networks. Final Year Project (FYP), Nanyang Technological University, Singapore. https://hdl.handle.net/10356/162869 https://hdl.handle.net/10356/162869 en SCSE21-0760 application/pdf Nanyang Technological University
institution	Nanyang Technological University
building	NTU Library
continent	Asia
country	Singapore Singapore
content_provider	NTU Library
collection	DR-NTU
language	English
topic	Engineering::Computer science and engineering
spellingShingle	Engineering::Computer science and engineering Tan, Ryan Kang Wei Visualizing interpretations of deep neural networks
description	Deep neural networks are notoriously black boxes that defy human interpretations. The lack of understanding of the decision process of neural networks erode public trust and prevent wide application of AI. In this project, we will develop a set of tools that visualize interpretations of deep neural networks, so that the general public can intuitively understand how these networks make decisions. For example, for a given prediction made by the network, we can visualize how data points in the training set affect the prediction.
author2	Li Boyang
author_facet	Li Boyang Tan, Ryan Kang Wei
format	Final Year Project
author	Tan, Ryan Kang Wei
author_sort	Tan, Ryan Kang Wei
title	Visualizing interpretations of deep neural networks
title_short	Visualizing interpretations of deep neural networks
title_full	Visualizing interpretations of deep neural networks
title_fullStr	Visualizing interpretations of deep neural networks
title_full_unstemmed	Visualizing interpretations of deep neural networks
title_sort	visualizing interpretations of deep neural networks
publisher	Nanyang Technological University
publishDate	2022
url	https://hdl.handle.net/10356/162869
_version_	1751548561007312896

Visualizing interpretations of deep neural networks

Similar Items