Comparison of learning algorithms for handwritten digit recognition

By Yann LeCun, L. Jackel, L. Eon Bottou, A. Brunot, Corinna Cortes, John S. Denker, Harris Drucker, Isabelle M Guyon, Urs Muller, Eduard Säckinger and 2 more. 1995

Subfields: Computer Vision and Pattern Recognition

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Computer Vision and Pattern Recognition

Citations in the corpus

Evasion Attacks against Machine Learning at Test Time (2013, methodology): “Similar to Globerson and Roweis [12], we consider discriminating between two distinct digits from the MNIST dataset [18].”
Poisoning Attacks against Support Vector Machines (2012, methodology): “We now quantitatively validate the eﬀectiveness of the proposed attack strategy on a well-known MNIST handwritten digit classiﬁcation task (LeCun et al., 1995).”
On Security and Sparsity of Linear Classifiers for Adversarial Settings (2016, methodology): “To visually show how evasion attacks work, we perform sparse and dense attacks on the MNIST digit data [21].”
Randomized Prediction Games for Adversarial Machine Learning (2016, background): “Similar to [21], we focus on two two-class subproblems of discriminating between two distinct digits from the MNIST data set [41], i.”
Security Evaluation of Support Vector Machines in Adversarial Environments (2014, methodology): “The experimental evaluation presented in the following sections demonstrates the behavior of our proposed method on an artificial two-dimensional dataset and evaluates its effectiveness on the classical MNIST handwritten digit recognition dataset [32, 45].”
Is data clustering in adversarial settings secure? (2013, methodology): “We finally repeat the experiments described in the previous sections on the MNIST handwritten digit data [21].”
Discriminative Neural Sentence Modeling by Tree-Based Convolution (2015, background): “Convolutional neural networks (CNNs), early used for image processing (LeCun, 1995), turn out to be effective with natural languages as well.”
To Fall Or Not To Fall: A Visual Approach to Physical Stability Prediction (2016, positive): “In a pilot study, we tested on a subset of the generated data with LeNet [16], a relatively small network designed for digit recognition, AlexNet [15], a large network and VGG Net[27], a even larger network than AlexNet.”
TI-POOLING: Transformation-Invariant Pooling for Feature Learning in Convolutional Neural Networks (2016, background): “This structural information serves for internal regularization through weight sharing in convolutional layers [17].”
Atomic Convolutional Networks for Predicting Protein-Ligand Binding Affinity (2017, methodology): “All ACNN core set models were trained with 15 atom types, 3 radial filters, and a (32, 32, 16) pyramidal atomistic fully-connected layer.”
Dataset Shift in Machine Learning (2009, methodology): “We applied FDROP to the MNIST dataset [LeCun et al., 1995] of handwritten digits, and focused on binary problems with small training sets of 50 samples per digit.”
An empirical evaluation of supervised learning in high dimensions (2008, unknown): “LeCun, Y., Jackel, L., Bottou, L., Brunot, A., Cortes, C., Denker, J., Drucker, H., Guyon, I., Muller, U., Sackinger, E., et al. (1995).”
Human Activity Recognition on Smartphones Using a Multiclass Hardware-Friendly Support Vector Machine (2012, methodology): “Although it is not fully clear which method performs better for AR, SVMs have confirmed successful application in several areas including heterogeneous types of recognition such as handwritten characters [9] and speech [10].”
Learning Transferable Knowledge Through Embedding Spaces (2019, methodology): “We investigate the empirical performance of our proposed method on three commonly used benchmarks digit classification datasets in UDA, namely: MNIST (M) [135], USPS (U ) [136], and Street View House Numbers (SVHN) (S).”
Deep Learning with Convolutional Neural Networks Applied to Electromyography Data: A Resource for the Classification of Movements for Prosthetic Hands (2016, methodology): “The convolutional neural network consisted of a modified version of a well known convolutional neural network (LeNet; LeCun et al., 1995), according to the implementation suggested for Cifar-10 in the package MatConvNet (Vedaldi and Lenc, 2015).”
Adversaries or allies? Privacy and deep learning in big data era (2018, methodology): “27 It is a large commonly used handwritten digits database.”
Distance Metric Learning for Large Margin Nearest Neighbor Classification (2006, methodology): “On MNIST, we used a non-homogeneous polynomial kernel of degree four, which gave us our best results, as also reported in LeCun et al. (1995).”