A good model of object shape is essential in applications such as segmentation, object detection, inpainting and graphics. For example, when performing segmentation, local constra...
We introduce VLADYMIR, a matrix library that permits the development of array-based code in C++. It is especially useful for numerical simulation tasks and parallelises automatical...
A new algorithm for training Restricted Boltzmann Machines is introduced. The algorithm, named Persistent Contrastive Divergence, is different from the standard Contrastive Diverg...
In this paper we present a method for learning classspecific
features for recognition. Recently a greedy layerwise
procedure was proposed to initialize weights of deep
belief ne...
Mohammad Norouzi (Simon Fraser University), Mani R...
We assess the generative power of the mPoTmodel of [10] with tiled-convolutional weight sharing as a model for visual textures by specifically training on this task, evaluating m...