Publication Date
Fall 2021
Degree Type
Thesis
Degree Name
Master of Arts (MA)
Department
Mathematics and Statistics
Advisor
Kyle Hambrook
Subject Areas
Mathematics
Abstract
We investigate two ideas in this thesis. First, we analyze the results of adaptingrecovery algorithms from linear inverse problems to defend neural networks against adversarial attacks. Second, we analyze the results of substituting sparsity priors with neural network priors in linear inverse problems. For the former, we are able to extend the framework introduced in [1] to defend neural networks against ℓ0, ℓ2,and ℓ∞ norm attacks, and for the latter, we find that our method yields an improvement over reconstruction results of [2].
Recommended Citation
Dhaliwal, Jasjeet, "Linear Inverse Problems and Neural Networks" (2021). Master's Theses. 5228.
DOI: https://doi.org/10.31979/etd.wfjb-2m4y
https://scholarworks.sjsu.edu/etd_theses/5228
