Y
Y. Le Cun
Researcher at Bell Labs
Publications - 16
Citations - 1297
Y. Le Cun is an academic researcher from Bell Labs. The author has contributed to research in topics: Artificial neural network & Time delay neural network. The author has an hindex of 11, co-authored 16 publications receiving 1173 citations.
Papers
More filters
Journal ArticleDOI
Handwritten digit recognition: applications of neural network chips and automatic learning
Y. Le Cun,Lawrence D. Jackel,Bernhard E. Boser,John S. Denker,Hans Peter Graf,Isabelle Guyon,D. Henderson,Richard Howard,W. Hubbard +8 more
TL;DR: Two novel methods for achieving handwritten digit recognition are described, based on a neural network chip that performs line thinning and feature extraction using local template matching and on a digital signal processor that makes extensive use of constrained automatic learning.
Proceedings ArticleDOI
Handwritten zip code recognition with multilayer networks
Y. Le Cun,O. Matan,Bernhard E. Boser,John S. Denker,D. Henderson,Richard Howard,W. Hubbard,L.D. Jacket,Henry S. Baird +8 more
TL;DR: An application of back-propagation networks to handwritten zip code recognition is presented, and the performance on zip code digits provided by the US Postal Service is 92% recognition, 1% substitution, and 7% rejects.
Journal ArticleDOI
Design of a neural network character recognizer for a touch terminal
TL;DR: A system which can recognize digits and uppercase letters handprinted on a touch terminal is described, analogous to “time delay neural networks” previously applied to speech recognition.
Journal ArticleDOI
An analog neural network processor with programmable topology
TL;DR: The architecture, implementation, and applications of a special-purpose neural network processor are described and the practicality of the chip is demonstrated with an implementation of a neural network for optical character recognition.
Proceedings ArticleDOI
Double backpropagation increasing generalization performance
H. Drucker,Y. Le Cun +1 more
TL;DR: It is shown that a training algorithm termed double back- Propagation improves generalization by simultaneously minimizing the normal energy term found in back-propagation and an additional energy term that is related to the sum of the squares of the input derivatives (gradients).