Yann LeCun, Chief AI Scientist, Meta Jacob T. Schwartz Professor of Computer Science, Data Science, Neural Science, and Electrical and Computer Engineering, New York University. ACM Turing Award Laureate, (sounds like I'm bragging, but a condition of accepting the award is to write this next to your name)

Happy hacking. The digit images in the MNIST set were originally selected and experimented with by Chris Burges and Corinna Cortes using bounding-box normalization and centering. Yann LeCun's version which is provided on this page uses centering by center of mass within in a larger window. Yann LeCun, Professor

In Proc. of Computer Vision and Pattern Recognition, Puerto-Rico, 1997. IEEE. [LeCun et al., 1997] Y. LeCun, L. Bottou, and Y. Bengio. Reading checks with graph transformer networks. In International Conference on Acoustics, Speech, and Signal Processing, volume 1, pages 151-154, Munich, 1997. IEEE. [LeCun and Bengio, 1995a] Y. LeCun and Y. Bengio.

The band I played with in high school and college (1975 to 1983) was called Ensemble de Musique Ancienne de Bury, and composed of 12 amateur musicians, many of whom are now professional musician: Jean-Jacques Dubayle (band leader, recorders, krumhorns, harpsichord), Christophe Aubry (violin), Philippe Baudin (recorders), Antoine Courtecuisse ...

Stroke Width Invariance The robustness to stroke width variation allows LeNet-5 to operate directly on "raw" pixel images without requiring unreliable preprocessing such as line thinning.

DjVu was developed at AT&T Labs in Red Bank NJ by a research team composed of Yann LeCun, Leon Bottou, Patrick Haffner, Paul Howard, Pascal Vincent, Yoshua Bengio, and Bill Riemers.

Yann LeCun, VP and Chief AI Scientist, Facebook Silver Professor of Computer Science, Data Science, Neural Science, and Electrical and Computer Engineering, New York University.

"Yann" is the Breton form of Ian/John/Jean/Jan/Johannes in Irish/English/French/Dutch/German. The French pronounce it "Yahn", but the real Bretons pronounce it "Yawnn" with a short "awn" and a long "n".

SDNN and Overlapping Characters A demonstration of feature binding, object segmentation, distortion invariance, and noise resistance. Features are bound into an object if the combination forms a recognizable object. Yann LeCun

Yann LeCun's home page at AT&T Labs: neural nets, OCR, and DjVu