Papers

Total 69 · Clear filters

1. 1998

   MNIST database of handwritten digits

   Proceedings of the IEEE

   MNIST is a database of 60,000 training and 10,000 test images of handwritten digits, normalized to 28×28 pixels and described in the 1998 paper by LeCun and colleagues as a shared benchmark for document recognition.

   Research historyDeep learningComputer vision

2. 1995

   Support-vector networks

   Machine Learning

   Corinna Cortes and Vladimir Vapnik's 1995 paper presents a learning machine for two-group classification that maps inputs nonlinearly into a high-dimensional feature space, constructs a linear decision surface, and extends earlier work from separable to non-separable data.

   Research historyDeep learningData & datasets

3. 1993

   Building a Large Annotated Corpus of English: The Penn Treebank

   Computational Linguistics

   A 1993 journal article by Mitchell P. Marcus, Beatrice Santorini and Mary Ann Marcinkiewicz describing the Penn Treebank: over one million words of Wall Street Journal text annotated with syntactic bracketing, built as a resource for work on English sentence structure.

   Large language modelsResearch historyData & datasets

4. 1992

   A Training Algorithm for Optimal Margin Classifiers

   Published in 1992, this paper by Boser, Guyon and Vapnik presents a training algorithm that maximizes the margin between training patterns and the decision boundary, with experiments on optical character recognition.[^1]

   Research historyDeep learningData & datasets

5. 1992

   Q-learning

   Machine Learning

   A 1992 technical note by Watkins and Dayan that set out Q-learning, an incremental and computationally light way for an agent to learn optimal action values, and proved it converges to the optimum with probability 1.

   Research historyDeep learningData & datasets

6. 1989

   Backpropagation Applied to Handwritten Zip Code Recognition

   Neural Computation

   In 1989 LeCun and colleagues at AT&T Bell Laboratories trained a convolutional network with backpropagation to read handwritten zip-code digits from U.S. mail, reaching 5.0% test error. The work showed that the convolutional design could be learned end to end on a real task.

   Research historyDeep learningComputer vision

7. 1988

   ALVINN: An Autonomous Land Vehicle in a Neural Network

   ANIPS11

   A 3-layer back-propagation network that takes camera and laser range finder images and outputs the direction to steer, trained on simulated road images and tested on Carnegie Mellon's autonomous navigation test vehicle.

   Research historyRoboticsComputer vision

8. 1958

   The Perceptron: A Probabilistic Model for Information Storage and Organization in the Brain

   Psychological Review

   In 1958 Frank Rosenblatt described the perceptron, a model whose connection strengths change with training so that it learns to classify stimuli by trial and error. It became the starting point for trainable neural networks.

   Research historyDeep learningComputer vision

9. 1948

   A Mathematical Theory of Communication

   Bell System Technical Journal 27

   C. E. Shannon's 1948 paper set out a mathematical framework for communication, defining information in bits, channel capacity, and entropy, and treating messages statistically while setting aside semantic meaning.

   Research historyData & datasetsScience