P. Simard

Publications
Influence

Learning long-term dependencies with gradient descent is difficult

Yoshua Bengio, P. Simard, P. Frasconi
Computer Science, Medicine
IEEE Trans. Neural Networks
1 March 1994

We show why gradient based learning algorithms face an increasingly difficult problem as the duration of the dependencies to be captured increases. Expand

4,969
230
PDF

Best practices for convolutional neural networks applied to visual document analysis

P. Simard, David Steinkraus, John C. Platt
Computer Science
Seventh International Conference on Document…
3 August 2003

This paper describes a set of concrete bestpractices that document analysis researchers can use toget good results with neural networks. Expand

2,052
134
PDF

Comparison of learning algorithms for handwritten digit recognition

Y. LeCun, L. Jackel, +9 authors V. Vapnik
Computer Science
1995

This paper compares the relative merits of several classi cation algorithms developed at Bell Laboratories and elsewhere for the purpose of recognizing handwritten digits. Expand

Counterfactual reasoning and learning systems: the example of computational advertising

L. Bottou, J. Peters, +6 authors Ed Snelson
Computer Science
J. Mach. Learn. Res.
2013

This work shows how to leverage causal inference to understand the behavior of complex learning systems interacting with their environment and predict the consequences of changes to the system. Expand

Efficient Pattern Recognition Using a New Transformation Distance

P. Simard, Y. LeCun, J. Denker
Mathematics, Computer Science
NIPS
30 November 1992

We propose a new distance measure which can be made locally invariant to any set of transformations of the input and (b) can be computed efficiently. Expand

Learning algorithms for classification: A comparison on handwritten digit recognition

Y. LeCun, L. Jackel, +8 authors V. Vapnik
Computer Science
1995

This paper compares the performance of several classi er algorithms on a standard database of handwritten digits. Expand

Comparison of classifier methods: a case study in handwritten digit recognition

L. Bottou, Corinna Cortes, +8 authors V. Vapnik
Computer Science
Proceedings of the 12th IAPR International…
9 October 1994

This paper compares the performance of several classifier algorithms on a standard database of handwritten digits with respect to training time, recognition time, and memory requirements. Expand

Transformation Invariance in Pattern Recognition-Tangent Distance and Tangent Propagation

P. Simard, Y. LeCun, J. Denker, B. Victorri
Computer Science, Mathematics
Neural Networks: Tricks of the Trade
1996

We introduce the concept of tangent vectors, which compactly represent the essence of these transformation invariances, and two classes of algorithms, “Tangent distance” and ‘Tangent propagation”, which make use of theseinvariances to improve performance. Expand

High quality document image compression with "DjVu"

L. Bottou, P. Haffner, P. Howard, P. Simard, Yoshua Bengio, Y. LeCun
Computer Science
J. Electronic Imaging
1 July 1998

We present a new image compression technique called \DjVu " that is speci cally geared towards the compression of high-resolution, high-quality images of scanned documents in color. Expand

Time is of the essence: a conjecture that hemispheric specialization arises from interhemispheric conduction delay.

J. Ringo, R. Doty, S. Demeter, P. Simard
Psychology, Medicine
Cerebral cortex
1 July 1994

Tomasch (1954) and Aboitiz et al. (1992) found the majority of the fibers of the human corpus callosum are under 1 micron in diameter. Electron microscopic studies of Swadlow et al. (1980) and the… Expand

Recommended Authors