We present an algorithm and package, Redistributor, which forces a colle...
Neural network training is usually accomplished by solving a non-convex
...
Although for neural networks with locally Lipschitz continuous activatio...
We present a novel technique based on deep learning and set theory which...
Deep neural networks have become state-of-the-art technology for a wide ...
We show that finite-width deep ReLU neural networks yield rate-distortio...