Robust Large Margin Approaches for Machine Learning in Adversarial Settings
Machine learning algorithms are invented to learn from data and to use data to perform predictions and analyses. Many agencies are now using machine learning algorithms to present services and to perform tasks that used to be done by humans. These services and tasks include making high-stake decisio...
Main Author: | Torkamani, MohamadAli |
---|---|
Other Authors: | Lowd, Daniel |
Language: | en_US |
Published: |
University of Oregon
2016
|
Subjects: | |
Online Access: | http://hdl.handle.net/1794/20677 |
Similar Items
-
Scaleable input gradient regularization for adversarial robustness
by: Chris Finlay, et al.
Published: (2021-03-01) -
On the Relationship between Generalization and Robustness to Adversarial Examples
by: Anibal Pedraza, et al.
Published: (2021-05-01) -
Perspectives on Adversarial Classification
by: David Rios Insua, et al.
Published: (2020-11-01) -
Distributionally Robust Optimization and its Applications in Machine Learning
by: Kang, Yang
Published: (2017) -
Adversarial Robustness by One Bit Double Quantization for Visual Classification
by: Maungmaung Aprilpyone, et al.
Published: (2019-01-01)