Multi-column deep neural networks for image classification

  title={Multi-column deep neural networks for image classification},
  author={Dan C. Ciresan and Ueli Meier and J{\"u}rgen Schmidhuber},
  journal={2012 IEEE Conference on Computer Vision and Pattern Recognition},
Traditional methods of computer vision and machine learning cannot match human performance on tasks such as the recognition of handwritten digits or traffic signs. [] Key Result We also improve the state-of-the-art on a plethora of common image classification benchmarks.
Very Deep Neural Network for Handwritten Digit Recognition
By a carefully crafted design, this paper proposed a new very deep neural network architecture for handwritten digit recognition that did not depart from the classical convolutional neural networks architecture, but pushed it to the limit by substantially increasing the depth.
Deep Columnar Convolutional Neural Network
The proposed model is a single deep and wide neural network architecture that offers near state-of-the-art performance on various image classification challenges, such as the MNIST dataset and the CIFAR-10 and CIFar-100 datasets.
Deep Neural Networks for Handwritten Chinese Character Recognition
This work extensively explore the performance of those networks for handwritten Chinese characters recognition (HCCR) based on popular convolutional neural networks architectures that are commonly used for large-scale image recognition and employs several distinct architectural fusion methods, resulting in more than 18 classification approaches.
Fast, Simple and Accurate Handwritten Digit Classification by Training Shallow Neural Network Classifiers with the ‘Extreme Learning Machine’ Algorithm
Close to state-of-the-art results for MNIST and NORB suggest that the ease of use and accuracy of the ELM algorithm for designing a single-hidden-layer neural network classifier should be given greater consideration either as a standalone method for simpler problems, or as the final classification stage in deep neural networks applied to more difficult problems.
Convolutional Neural Network with Multi-column Characteristics Extraction for Image Classification
This paper proposes a convolutional network architecture with a performance-enhancing approach, a hierarchical structure that is easy to build, adaptive, and easy to train with good performance in image classification tasks.
Recognition of Handwritten Digit using Convolutional Neural Network in Python with Tensorflow and Comparison of Performance for Various Hidden Layers
The goal of this paper is to observe the variation of accuracies of CNN to classify handwritten digits using various numbers of hidden layers and epochs and to make the comparison between the accuracies.
Deep Fisher Networks for Large-Scale Image Classification
This paper proposes a version of the state-of-the-art Fisher vector image encoding that can be stacked in multiple layers, and significantly improves on standard Fisher vectors, and obtains competitive results with deep convolutional networks at a smaller computational learning cost.
Spatially-sparse convolutional neural networks
A CNN for processing spatially-sparse inputs, motivated by the problem of online handwriting recognition, and applying a deep convolutional network using sparsity has resulted in a substantial reduction in test error on the CIFAR small picture datasets.
Fast, simple and accurate handwritten digit classification using extreme learning machines with shaped input-weights
This report shows that published deep network results on the MNIST handwritten digit dataset can straightforwardly be replicated with shallow ELM networks, and suggests that the ease of use and accuracy of ELM should be given greater consideration as an alternative to deep networks applied to more challenging datasets.
On Binary Classification with Single-Layer Convolutional Neural Networks
It is presented that using such a simple and relatively fast model for classifying cats and dogs, performance is close to state-of-the-art achievable by a combination of SVM models on color and texture features.


Flexible, High Performance Convolutional Neural Networks for Image Classification
We present a fast, fully parameterizable GPU implementation of Convolutional Neural Network variants. Our feature extractors are neither carefully designed nor pre-wired, but rather learned in a
Convolutional Neural Network Committees for Handwritten Character Classification
This work applies the same architecture to NIST SD 19, a more challenging dataset including lower and upper case letters, and obtains the best results published so far for both NIST digits and NIST letters.
GradientBased Learning Applied to Document Recognition
Various methods applied to handwritten character recognition are reviewed and compared and Convolutional Neural Networks, that are specifically designed to deal with the variability of 2D shapes, are shown to outperform all other techniques.
Large-scale object recognition with CUDA-accelerated hierarchical neural networks
  • Rafael Uetz, Sven Behnke
  • Computer Science
    2009 IEEE International Conference on Intelligent Computing and Intelligent Systems
  • 2009
This work presents a hierarchical, locally-connected neural network model that is well-suited for large-scale, high-performance object recognition and creates a massively parallel implementation of the model which is executed on a state-of-the-art graphics card.
Learning Multiple Layers of Features from Tiny Images
It is shown how to train a multi-layer generative model that learns to extract meaningful features which resemble those found in the human visual cortex, using a novel parallelization algorithm to distribute the work among multiple machines connected on a network.
Gradient-based learning applied to document recognition
This paper reviews various methods applied to handwritten character recognition and compares them on a standard handwritten digit recognition task, and Convolutional neural networks are shown to outperform all other techniques.
Deep, Big, Simple Neural Nets for Handwritten Digit Recognition
Good old online backpropagation for plain multilayer perceptrons yields a very low 0.35 error rate on the MNIST handwritten digits benchmark. All we need to achieve this best result so far are many
Traffic sign recognition with multi-scale Convolutional Networks
This work applies Convolutional Networks (ConvNets) to the task of traffic sign classification as part of the GTSRB competition, and yields the 2nd-best accuracy above the human performance.
Evaluation of Pooling Operations in Convolutional Architectures for Object Recognition
The aim is to gain insight into different functions by directly comparing them on a fixed architecture for several common object recognition tasks, and empirical results show that a maximum pooling operation significantly outperforms subsampling operations.
Unsupervised Learning of Invariant Feature Hierarchies with Applications to Object Recognition
An unsupervised method for learning a hierarchy of sparse feature detectors that are invariant to small shifts and distortions that alleviates the over-parameterization problems that plague purely supervised learning procedures, and yields good performance with very few labeled training samples.