Yann LeCun

Research topics

• Neural Networks and Applications · 2 papers
• Handwritten Text Recognition Techniques · 2 papers
• Image Processing and 3D Reconstruction · 1 paper
• Geophysical Methods and Applications · 1 paper

Frequent co-authors

• Léon Bottou · 1 paper
• Yoshua Bengio · 1 paper
• Patrick Haffner · 1 paper
• Bernhard E. Boser · 1 paper
• John S. Denker · 1 paper
• D. Henderson · 1 paper
• Richard E. Howard · 1 paper
• W. Hubbard · 1 paper

Papers

1. Gradient-based learning applied to document recognitionProceedings of the IEEE · 1998 · 59,951 citations

   Multilayer neural networks trained with the back-propagation algorithm constitute the best example of a successful gradient based learning technique. Given an appropriate network architecture, gradient-based learning algorithms can be used to synthesize a complex decision surface that can classify high-dimensional…

2. Backpropagation Applied to Handwritten Zip Code RecognitionNeural Computation · 1989 · 12,221 citations

   The ability of learning networks to generalize can be greatly enhanced by providing constraints from the task domain. This paper demonstrates how such constraints can be integrated into a backpropagation network through the architecture of the network. This approach has…