Files in this item



application/pdfDIMON-THESIS-2021.pdf (3MB)
(no description provided)PDF


Title:Unsupervised anomaly detection in multi-class datasets using Generative Adversarial Networks
Author(s):Dimon, Walker Lee
Advisor(s):Lembeck, Michael F; Tran, Huy T
Department / Program:Aerospace Engineering
Discipline:Aerospace Engineering
Degree Granting Institution:University of Illinois at Urbana-Champaign
Subject(s):Generative Adversarial Networks, Unsupervised Anomaly Detection, Computer Vision, Unsupervised Learning, Machine Learning
Abstract:Presented in this thesis is a novel Generative Adversarial Network, or GAN, based method, D-AnoGAN, for detecting anomalies in complex datasets containing disconnected data manifolds. Current state-of-the-art methods treat disconnected data manifolds as a single, continuous one to learn from. The key contribution of D-AnoGAN is specifically accounting for the discontinuity between manifolds within a dataset during training. To achieve this, a multi-generator network is first implemented, where each generator is responsible for learning a unique manifold of data. Second, a machine learning mechanism called a ''bandit" is implemented to find the optimal set of generators required to cover all data manifolds through unsupervised prior-learning. Finally, the multi-generator and bandit are used to cluster data from the same manifold together during training, allowing them to be learned in a disconnected fashion. The proposed method's effectiveness is demonstrated on two publicly available datasets, as well as a new experimental dataset developed in-house, where state-of-the-art results are achieved.
Issue Date:2021-04-28
Rights Information:Copyright 2021 Walker Dimon
Date Available in IDEALS:2021-09-17
Date Deposited:2021-05

This item appears in the following Collection(s)

Item Statistics