Abstract-The information era has brought with it the wellknown problem of 'Information Explosion'. There are many and varied search engines on the Internet but it is stil...
: The main idea behind Reconfigurable Object Nets (RONs) is to support the visual specification of controlled rule-based net transformations of place/transition nets (P/T nets). RO...
Most illuminant estimation algorithms work with the assumption of one specific type of the light source (e.g. point light source or directional light source). This assumption brin...
We have developed a machine learning toolbox, called SHOGUN, which is designed for unified large-scale learning for a broad range of feature types and learning settings. It offers...
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...