Where do features come from?
Cognitive Science Society Annual Conference, pp. 1078-1101, 2014.
boltzmann machinesvariational learninglearning graphical modelsbackpropagationcontrastive divergenceMore(3+)
It is possible to learn multiple layers of non-linear features by backpropagating error derivatives through a feedforward neural network. This is a very effective learning procedure when there is a huge amount of labeled training data, but for many learning tasks very few labeled examples are available. In an effort to overcome the need f...More
Full Text (Upload PDF)
PPT (Upload PPT)