Show simple item record

dc.contributor.advisorChau, Duen Horng
dc.contributor.authorZhou, Zhiyan
dc.date.accessioned2022-05-27T14:37:37Z
dc.date.available2022-05-27T14:37:37Z
dc.date.created2022-05
dc.date.submittedMay 2022
dc.identifier.urihttp://hdl.handle.net/1853/66715
dc.description.abstractDeep neural networks are often considered as black box models. One of the reasons is that they have a large number of parameters. Understanding the model through these parameters is often a hard task. Recent advances in nonlinear dimensionality reduction techniques offer a better way to visualize high-dimensional nonlinear data[1]. These techniques have the potential of helping people understand deep neural networks. However, many of these techniques pose problems, such as indeterministic results and slower computation. These problems prevent them from being used in visualizing the training dynamic of deep neural networks[2]. Neuro-Mapper attempts to tackle this through the use of scalable data visualization technologies and Aligned UMAP, a special kind of UMAP that is able to generate embeddings that are aligned with each other[3]. Users can explore the training behavior of a model using NeuroMapper and adjust the hyperparameter as they see fit. NeuroMapper works across multiple platforms and can visualize more than 40000 data points.
dc.format.mimetypeapplication/pdf
dc.publisherGeorgia Institute of Technology
dc.subjectNeural Network
dc.subjectData Visualization
dc.subjectDimensionality Reduction
dc.titleNeuroMapper: Using UMAP to visualize the training dynamic of neural network
dc.typeUndergraduate Research Option Thesis
dc.description.degreeUndergraduate
dc.contributor.departmentComputer Science
thesis.degree.levelUndergraduate
dc.contributor.committeeMemberYang, Diyi
dc.date.updated2022-05-27T14:37:38Z


Files in this item

Thumbnail

This item appears in the following Collection(s)

Show simple item record