2 code implementations • ICLR 2018 • Murat Kocaoglu, Christopher Snyder, Alexandros G. Dimakis, Sriram Vishwanath
We show that adversarial training can be used to learn a generative model with true observational and interventional distributions if the generator architecture is consistent with the given causal graph.
no code implementations • 5 Nov 2018 • Christopher Snyder, Sriram Vishwanath
The paper shows that the number of support vectors s relates with learning guarantees for neural networks through sample compression bounds, yielding a sample complexity of O(ns/epsilon) for networks with n neurons.
no code implementations • 25 Mar 2020 • Christopher Snyder, Sriram Vishwanath
We improve the generalization of an already trained network by interpreting, diagnosing, and replacing components the logical circuit that is the DNN.
no code implementations • 26 Jun 2020 • Christopher Snyder, Sriram Vishwanath
A generalizable impact beyond ECGs lies in the ability to provide a rich test-bed for the development of interpretive techniques in medicine.