— In this paper, we investigate the use of a spherical projection model to search for optimal visual features for visual servoing. A new minimal set of three visual features is p...
Usually, in traditional text categorization systems based on Vector Space Model, there is no context information in a feature vector, which limited the performance of the system. T...
A crucial issue for Machine Learning and Data Mining is Feature Selection, selecting the relevant features in order to focus the learning search. A relaxed setting for Feature Sele...
Many current object class models build on visual parts that constitute an object. However, visually different entities may actually refer to the same object part. This may be harm...
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...