We propose a new neural network architecture, called Simple Recurrent Temporal-Difference Networks (SR-TDNs), that learns to predict future observations in partially observable en...
Previous work has shown that the difficulties in learning deep generative or discriminative models can be overcome by an initial unsupervised learning step that maps inputs to use...
Pascal Vincent, Hugo Larochelle, Yoshua Bengio, Pi...
We present a discrete spectral framework for the sparse or cardinality-constrained solution of a generalized Rayleigh quotient. This NPhard combinatorial optimization problem is c...
Current object group selection techniques such as lasso or rectangle selection can be time consuming and error prone. This is apparent when selecting distant objects on a large di...
This paper introduces a novel way to enhance input devices to sense a user's foot motion. By measuring the electrostatic potential of a user, this device can sense the user...