Yann LeCun is a computer scientist whose research interests include computational and biological models of learning and perception.
One of his goals is to understand the principles of learning in the brain, and to build computational models with similar learning abilities. His research is primarily applied to artificial vision, allowing computers to recognize objects in images, and allowing mobile robots to navigate using vision. He also applies his large-scale learning algorithms to other domains, such as predicting epilepsy seizures from EEG signal, predicting data with spatio-temporal dependencies such as real estate prices, and identifying sub-cellular structures in biological images.
In past decades, LeCun worked on document understanding and OCR, as well as on data compression and digital libraries. His image compression technology, called DjVu, is used by numerous digital libraries and publishers, including the Internet Archive and The New Yorker, to distribute scanned documents online or on DVD. His handwriting recognition technology, which uses a biologially inspired learning system, has been used commercially since the mid-1990s in bank cheque-reading machines. It automatically processes a large percentage of bank cheques in the United States. His learning-based image understanding techniques are used in many industrial applications, including video surveillance, document understanding and human-computer interaction.
- ACM A.M. Turing Award, 2018
- IEEE Neural Network Pioneer Award, 2014
- Director of AI Research, Facebook, 2013
Vapnil, V. et al. “Measuring the VC-dimension of a learning machine.” Neural Comput. 6, no. 5 (1994): 851–76.
CIFAR is a registered charitable organization supported by the governments of Canada, Alberta and Quebec, as well as foundations, individuals, corporations and Canadian and international partner organizations.