no code implementations • ICLR 2019 • Klas Leino, Emily Black, Matt Fredrikson, Shayak Sen, Anupam Datta
This overestimation gives rise to feature-wise bias amplification -- a previously unreported form of bias that can be traced back to the features of a trained model.
no code implementations • 28 Mar 2018 • Shayak Sen, Piotr Mardziel, Anupam Datta, Matthew Fredrikson
Standard methods for training classifiers that minimize empirical risk do not constrain the behavior of the classifier on such datapoints.
2 code implementations • ICLR 2018 • Klas Leino, Shayak Sen, Anupam Datta, Matt Fredrikson, Linyi Li
We study the problem of explaining a rich class of behavioral properties of deep neural networks.
no code implementations • 29 Nov 2017 • Anupam Datta, Sophia Kovaleva, Piotr Mardziel, Shayak Sen
The interpretation of latent factors can then replace the uninterpreted latent factors, resulting in a new model that expresses predictions in terms of interpretable features.
no code implementations • 27 Sep 2017 • Linyi Li, Matt Fredrikson, Shayak Sen, Anupam Datta
In this report, we applied integrated gradients to explaining a neural network for diabetic retinopathy detection.
3 code implementations • 25 Jul 2017 • Anupam Datta, Matt Fredrikson, Gihyuk Ko, Piotr Mardziel, Shayak Sen
Machine learnt systems inherit biases against protected classes, historically disparaged groups, from training data.
no code implementations • 22 May 2017 • Anupam Datta, Matthew Fredrikson, Gihyuk Ko, Piotr Mardziel, Shayak Sen
For a specific instantiation of this definition, we present a program analysis technique that detects instances of proxy use in a model, and provides a witness that identifies which parts of the corresponding program exhibit the behavior.
no code implementations • 23 Mar 2016 • Aleksandar Chakarov, Aditya Nori, Sriram Rajamani, Shayak Sen, Deepak Vijaykeerthy
Unlike traditional programs (such as operating systems or word processors) which have large amounts of code, machine learning tasks use programs with relatively small amounts of code (written in machine learning libraries), but voluminous amounts of data.