3 code implementations • NeurIPS 2020 • Huanrui Yang, Jingyang Zhang, Hongliang Dong, Nathan Inkawhich, Andrew Gardner, Andrew Touchet, Wesley Wilkes, Heath Berry, Hai Li
The process is hard, often requires models with large capacity, and suffers from significant loss on clean data accuracy.
no code implementations • 19 Nov 2019 • Javier Echauz, Keith Kenemer, Sarfaraz Hussein, Jay Dhaliwal, Saurabh Shintre, Slawomir Grzonkowski, Andrew Gardner
Machine learning models are vulnerable to adversarial inputs that induce seemingly unjustifiable errors.
no code implementations • 10 Sep 2017 • Andrew Gardner, Jinko Kanno, Christian A. Duncan, Rastko R. Selmic
Unordered feature sets are a nonstandard data structure that traditional neural networks are incapable of addressing in a principled manner.
no code implementations • 9 Oct 2015 • Andrew Gardner, Christian A. Duncan, Jinko Kanno, Rastko R. Selmic
Positive definite kernels are an important tool in machine learning that enable efficient solutions to otherwise difficult or intractable problems by implicitly linearizing the problem geometry.
no code implementations • CVPR 2014 • Andrew Gardner, Jinko Kanno, Christian A. Duncan, Rastko Selmic
We present a distance metric based upon the notion of minimum-cost injective mappings between sets.