With the goal to generate more scalable algorithms with higher efficiency and fewer open parameters, reinforcement learning (RL) has recently moved towards combining classical tec...
This paper proposes a simple voting scheme for off-line recognition of handprinted numerals. One of the main features of the proposed scheme is that this is not script dependent. ...
The training experiences needed by a learning system may be selected by either an external agent or the system itself. We show that knowledge of the current state of the learner...
We transform the outputs of each hidden neuron in a multi-layer perceptron network to have zero output and zero slope on average, and use separate shortcut connections to model th...
Models such as pairwise conditional random fields (CRFs) are extremely popular in computer vision and various other machine learning disciplines. However, they have limited expre...