Convolutional Neural Network Committees for Handwritten Character Classification

By Dan Claudiu Ciresan, Ueli Meier, Luca Maria Gambardella, J. Urgen Schmidhuber. 2011

513 citations recorded by the source corpus.

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

EMNIST: an extension of MNIST to handwritten letters (2017, neutral): “further validate their convolutional neural network [16].”
On Learning to Think: Algorithmic Information Theory for Novel Combinations of Reinforcement Learning Controllers and Recurrent Neural World Models (2015, background): “, MNIST (2011), won numerous competitions [247, 38, 41, 39, 161, 42, 36, 134, 322, 37, 245], and achieved the first human-competitive or even superhuman results on well-known benchmarks, e.”
Self-Delimiting Neural Networks (2012, background): “Additional 1st ranks were achieved in important machine learning (ML) benchmarks since 2010: (A) MNIST handwritten digits data set [38] (perhaps the most famous ML benchmark).”
Large-Scale Deep Learning on the YFCC100M Dataset (2015, background): “Neural networks have been shown to perform well in a wide variety of tasks, including text analysis [4], speech recognition [5, 6, 7], various classiﬁcation tasks [8, 9], and most notably unsupervised and supervised feature learning on natural imagery [1, 2, 3].”
Deep Neural Networks Segment Neuronal Membranes in Electron Microscopy Images (2012, background): “Lately, DNN proved their efficiency on data sets extending from handwritten digits (MNIST) [9, 11], handwritten characters [10] to 3D toys (NORB) [12] and faces [34].”
Transfer learning for Latin and Chinese characters with Deep Neural Networks (2012, methodology): “As in [16], we use rotation of max.”
Multi-column deep neural network for traffic sign classification (2012, background): “Initial experiments with varying network depths showed that deep nets work better than shallow ones, consistent with our previous work on image classification (Ciresan, Meier, Gambardella, & Schmidhuber, 2010 ; Ciresan et al., 2011a).”
Steel defect classification with Max-Pooling Convolutional Neural Networks (2012, unknown): “recognition benchmarks [5], [21], [22].”
Multi-Column Deep Neural Networks for Offline Handwritten Chinese Character Classification (2013, background): “It contains 224419 characters written by 60 persons.”