Multi-column deep neural networks for image classification

2012/06/01 by Dan Cireşan, Ueli Meier, Jürgen Schmidhuber · 20 citations
Computer Science · #Advanced Neural Network Applications #Artificial intelligence #Artificial neural network #Benchmark (surveying) #Computer science #Contextual image classification #Convolutional neural network #Deep learning #Domain Adaptation and Few-Shot Learning #Feature extraction #Graphics #Handwriting #Handwriting recognition #Image (mathematics) #MNIST database #Machine learning #Pattern recognition (psychology) #Sign (mathematics) #Traffic sign #Traffic sign recognition #Visual Attention and Saliency Detection

paper · doi:10.1109/cvpr.2012.6248110

openalex publication_date 2012/06/01 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/29

Abstract

Traditional methods of computer vision and machine learning cannot match human performance on tasks such as the recognition of handwritten digits or traffic signs. Our biologically plausible, wide and deep artificial neural network architectures can. Small (often minimal) receptive fields of convolutional winner-take-all neurons yield large network depth, resulting in roughly as many sparsely connected neural layers as found in mammals between retina and visual cortex. Only winner neurons are trained. Several deep neural columns become experts on inputs preprocessed in different ways; their predictions are averaged. Graphics cards allow for fast training. On the very competitive MNIST handwriting benchmark, our method is the first to achieve near-human performance. On a traffic sign recognition benchmark it outperforms humans by a factor of two. We also improve the state-of-the-art on a plethora of common image classification benchmarks.

Citations

• Evaluation of Pooling Operations in Convolutional Architectures for Object Recognition
• Gradient-based learning applied to document recognition
• Learning Multiple Layers of Features from Tiny Images
• Deep, Big, Simple Neural Nets for Handwritten Digit Recognition

Cited by

• SpinalNet: Deep Neural Network With Gradual Input
• DropSample: A New Training Method to Enhance Deep Convolutional Neural Networks for Large-Scale Unconstrained Handwritten Chinese Character Recognition
• Normalized Compression Distance of Multisets with Applications
• DeepTox: Toxicity Prediction using Deep Learning
• Facial attractiveness of cleft patients: a direct comparison between artificial-intelligence-based scoring and conventional rater groups
• Ensemble deep learning: A review
• PCANet: A Simple Deep Learning Baseline for Image Classification?
• Improved deep learning techniques in gravitational-wave data analysis
• DeepGauge: multi-granularity testing criteria for deep learning systems
• Two-stream Fusion Model for Dynamic Hand Gesture Recognition using 3D-CNN and 2D-CNN Optical Flow guided Motion Template
• Sill-Net: Feature Augmentation with Separated Illumination Representation
• Rapid Exact Signal Scanning With Deep Convolutional Neural Networks
• Fingertip detection and tracking for recognition of air-writing in videos
• Efficient-CapsNet: capsule network with self-attention routing
• Accurate pedestrian localization in overhead depth images via Height-Augmented HOG
• Propagation based phase retrieval of simulated intensity measurements using artificial neural networks
• Improvements to Context Based Self-Supervised Learning
• A Brief History of Artificial Intelligence Research
• Artificial intelligence [wikipedia]
• Neural network (machine learning) [wikipedia]

Related

• Assessing four Neural Networks on Handwritten Digit Recognition Dataset (MNIST)
• Deep, Big, Simple Neural Nets for Handwritten Digit Recognition
• Some Improvements on Deep Convolutional Neural Network Based Image Classification
• ImageNet classification with deep convolutional neural networks
• Massively Deep Artificial Neural Networks for Handwritten Digit Recognition