Goeffrey E. Hinton

Learn More
We present a system that separates text from graphics strokes in handwritten digital ink. It utilizes not just the characteristics of the strokes, but also the information provided by the gaps between the strokes, as well as the temporal characteristics of the stroke sequence. It is built using machine learning techniques that infer the internal parameters(More)
We describe a method for incrementally constructing a hierarchical generative model of an ensemble of binary data vectors. The model is composed of stochastic, binary, logistic units. Hidden units are added to the model one at a time with the goal of minimizing the information required to describe the data vectors using the model. In addition to the(More)
Shallow pattern inference systems necessitate a pre-processing stage whereby high-dimensional signals are mapped to a lower-dimension feature space that can be applied to standard classifiers. As a result, the intelligence of the system shifts to the feature extraction process, which is often imperfect and always application-domain specific. Deep machine(More)
  • 1