1
Recent works have shown that stochastic gradient descent (SGD) achieves the fast convergence rates of full-batch gradient descent for …
Markov Decision Processes (MDPs), the mathematical framework underlying most algorithms in Reinforcement Learning (RL), are often used …
We study the effect of the stochastic gradient noise on the training of generative adversarial networks (GANs) and show that it can …
Domain randomization is a popular technique for improving domain transfer, often used in a zero-shot setting when the target domain is …
Millions of blind and visually-impaired (BVI) people navigate urban environments every day, using smartphones for high-level …
Deep learning has thrived by training on large-scale datasets. However, in robotics applications sample efficiency is critical. We …
Single-view 3D shape reconstruction is an important but challenging problem, mainly for two reasons. First, as shape annotation is very …
We present a system for generating inconspicuous-looking textures that, when displayed in the physical world as digital or printed …
A major obstacle in instance segmentation is that existing methods often need many per-pixel labels in order to be effective. These …
Neural networks have become the state-of-the-art approach for machine translation (MT) in many languages. While …