Shift equivariance is a fundamental principle that governs how we percei...
Data augmentation is a critical contributing factor to the success of de...
Randomized Smoothing (RS), being one of few provable defenses, has been
...
Enforcing orthogonality in neural networks is an antidote for gradient
v...
Higher-order Recurrent Neural Networks (RNNs) are effective for long-ter...
Deep neural networks generalize well on unseen data though the number of...
Bayesian learning of model parameters in neural networks is important in...
Modern neural networks can have tens of millions of parameters, and are ...