Stars
Adversarial Attacks
Targeted Adversarial Examples on Speech-to-Text systems
Pytorch implementations of Bayes By Backprop, MC Dropout, SGLD, the Local Reparametrization Trick, KF-Laplace, SG-HMC and more
BackPACK - a backpropagation package built on top of PyTorch which efficiently computes quantities other than the gradient.
can calculate the Hessian matrix and/or its spectrum for simple neural nets
pyhessian is a TensorFlow module which can be used to estimate Hessian matrices
Implementation of TRPO and related algorithms
A PyTorch Library for Reinforcement Learning Research