Learning a hierarchy of patterns

Geoffrey Hinton

Geoffrey Hinton helped revive neural networks as a practical approach to machine learning. His work with collaborators advanced learning internal representations, backpropagation, Boltzmann machines, and deep networks. At the University of Toronto, his group helped demonstrate the power of large neural models for image recognition. His award, shared with Yoshua Bengio and Yann LeCun, recognized decades of conceptual and engineering progress that made deep learning influential.

Yann LeCun

Yann LeCun developed convolutional neural networks into effective systems for recognizing visual patterns. His work at Bell Labs combined trainable feature extraction with end-to-end learning, including applications to handwritten character recognition. At New York University and Facebook he continued research on representation learning and machine intelligence. His contribution to the joint deep-learning award particularly connects neural-network architecture with the engineering needed for useful perception systems.

Yoshua Bengio

Yoshua Bengio developed methods for learning useful representations in deep neural networks. His research helped establish distributed representations of language and investigated how deep architectures can learn complex structure from data. At the Université de Montréal, he also built a major research community around machine learning. His part in the joint award reflects sustained theoretical and experimental work that helped deep learning become a central approach to artificial intelligence.