We present a biologically inspired neural network model of visual orienting (using saccadic eye movements) in which targets are preferentially selected according to their reward va...
This paper proposes an unsupervised neural algorithm for trajectory production of a 6-DOF robotic arm. The model encodes these trajectories in a single training iteration by using...
Abstract: Structure learning of dynamic Bayesian networks provide a principled mechanism for identifying conditional dependencies in time-series data. This learning procedure assum...
This paper considers application of Deep Belief Nets (DBNs) to natural language call routing. DBNs have been successfully applied to a number of tasks, including image, audio and ...
Ruhi Sarikaya, Geoffrey E. Hinton, Bhuvana Ramabha...
— In many applications of supervised learning, the conditional average of the target variables is not sufficient for prediction. The dependencies between the explanatory variabl...