Statistical methods, such as independent component analysis, have been successful in learning local low-level features from natural image data. Here we extend these methods for le...
T h e ease of learning concepts f r o m examples in empirical machine learning depends on the attributes used for describing the training d a t a . We show t h a t decision-tree b...
Existing approaches to classifying documents by sentiment include machine learning with features created from n-grams and part of speech. This paper explores a different approach ...
We address the problem of multiclass object detection. Our aims are to enable models for new categories to benefit from the detectors built previously for other categories, and fo...
Restricted Boltzmann machines were developed using binary stochastic hidden units. These can be generalized by replacing each binary unit by an infinite number of copies that all ...