3 papers
stat.ML2018
Defending against Adversarial Images using Basis Functions Transformations
Uri Shaham, James Garritano, Yutaro Yamada +5
We study the effectiveness of various approaches that defend against adversarial attacks on deep networks via manipulations based on basis function representations of images. Speci…
stat.ML2018
SpectralNet: Spectral Clustering using Deep Neural Networks
Uri Shaham, Kelly Stanton, Henry Li +3
Spectral clustering is a leading and popular technique in unsupervised data analysis. Two of its major limitations are scalability and generalization of the spectral embedding (i.e…
stat.ML2016
Removal of Batch Effects using Distribution-Matching Residual Networks
Uri Shaham, Kelly P. Stanton, Jun Zhao +4
Sources of variability in experimentally derived data include measurement error in addition to the physical phenomena of interest. This measurement error is a combination of system…