Deep, Big, Simple Neural Nets for Handwritten Digit Recognition

  title={Deep, Big, Simple Neural Nets for Handwritten Digit Recognition},
  author={Dan C. Ciresan and U. Meier and L. Gambardella and J. Schmidhuber},
  journal={Neural Computation},
  • Dan C. Ciresan, U. Meier, +1 author J. Schmidhuber
  • Published 2010
  • Computer Science, Medicine
  • Neural Computation
  • 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 hidden layers, many neurons per layer, numerous deformed training images to avoid overfitting, and graphics cards to greatly speed up learning. 
    779 Citations
    Deep Big Multilayer Perceptrons for Digit Recognition
    • 43
    • PDF
    Handwritten Digit Recognition with a Committee of Deep Neural Nets on GPUs
    • 28
    • PDF
    Combining additive input noise annealing and pattern transformations for improved handwritten character recognition
    • 12
    • Highly Influenced
    Multi-column deep neural networks for image classification
    • 2,840
    • PDF
    Digit Recognition Using Convolution Neural Network
    Better Digit Recognition with a Committee of Simple Neural Nets
    • 69
    • PDF


    A trainable feature extractor for handwritten digit recognition
    • 275
    • Highly Influential
    • PDF
    Accelerating Large-Scale Convolutional Neural Networks with Parallel Graphics Multiprocessors
    • 52
    • PDF
    Gradient-based learning applied to document recognition
    • 25,583
    • Highly Influential
    • PDF
    Reducing the Dimensionality of Data with Neural Networks
    • 11,539
    • PDF
    Training Invariant Support Vector Machines
    • 567
    • Highly Influential
    • PDF
    Best practices for convolutional neural networks applied to visual document analysis
    • 1,954
    • Highly Influential
    • PDF
    Using GPUs for machine learning algorithms
    • 160
    • Highly Influential
    • PDF
    To recognize shapes, first learn to generate images.
    • 267
    • PDF