To recognize shapes, first learn to generate images

Gradient-based learning applied to document recognition

1998 • 49,688 citations

The Nature of Statistical Learning Theory

1995 • 38,742 citations

Learning representations by back-propagating errors

1986 • 25,825 citations

Reducing the Dimensionality of Data with Neural Networks

2006 • 18,756 citations

A Fast Learning Algorithm for Deep Belief Nets

2006 • 15,378 citations

The Nature of Statistical Learning Theory

2000 • 10,006 citations

Advances in Neural Information Processing Systems 19

2007 • 9,326 citations

Applied Optimal Control

2018 • 5,869 citations

Training Products of Experts by Minimizing Contrastive Divergence

2002 • 4,852 citations

Greedy Layer-Wise Training of Deep Networks

2007 • 4,621 citations

Perceptrons: An Introduction to Computational Geometry

1969 • 3,322 citations

Applied Optimal Control

1979 • 3,184 citations

Beyond regression : new fools for prediction and analysis in the behavioral sciences

1974 • 2,830 citations

Beyond Regression : "New Tools for Prediction and Analysis in the Behavioral Sciences

1974 • 2,472 citations

The Nature of Statistical Learning

1995 • 2,351 citations

Principles of Neurodynamics.

1963 • 2,287 citations

Learning methods for generic object recognition with invariance to pose and lighting

2004 • 1,321 citations

The "Wake-Sleep" Algorithm for Unsupervised Neural Networks

1995 • 1,100 citations

Efficient Learning of Sparse Representations with an Energy-Based Model

2007 • 1,055 citations

Topographic reorganization of somatosensory cortical areas 3b and 1 in adult monkeys following restricted deafferentation

1983 • 1,037 citations

Dependence on REM Sleep of Overnight Improvement of a Perceptual Skill

1994 • 993 citations

Untitled

2002 • 575 citations

Induction of visual orientation modules in auditory cortex

2000 • 547 citations

Pandemonium: a paradigm for learning

1988 • 486 citations

Learning in Spiking Neural Networks by Reinforcement of Stochastic Synaptic Transmission

2003 • 349 citations

A more biologically plausible learning rule for neural networks.

1991 • 230 citations

Weight perturbation: an optimal architecture and learning technique for analog VLSI feedforward and recurrent multilayer networks

1992 • 230 citations

Une procedure d'apprentissage pour reseau a seuil asymmetrique (A learning scheme for asymmetric threshold networks)

1985 • 109 citations