Stacked Convolutional Auto-Encoders for Hierarchical Feature Extraction

  • Jonathan Masci
  • Ueli Meier
  • Dan Cireşan
  • Jürgen Schmidhuber
Conference paper

DOI: 10.1007/978-3-642-21735-7_7

Part of the Lecture Notes in Computer Science book series (LNCS, volume 6791)
Cite this paper as:
Masci J., Meier U., Cireşan D., Schmidhuber J. (2011) Stacked Convolutional Auto-Encoders for Hierarchical Feature Extraction. In: Honkela T., Duch W., Girolami M., Kaski S. (eds) Artificial Neural Networks and Machine Learning – ICANN 2011. ICANN 2011. Lecture Notes in Computer Science, vol 6791. Springer, Berlin, Heidelberg

Abstract

We present a novel convolutional auto-encoder (CAE) for unsupervised feature learning. A stack of CAEs forms a convolutional neural network (CNN). Each CAE is trained using conventional on-line gradient descent without additional regularization terms. A max-pooling layer is essential to learn biologically plausible features consistent with those found by previous approaches. Initializing a CNN with filters of a trained CAE stack yields superior performance on a digit (MNIST) and an object recognition (CIFAR10) benchmark.

Keywords

convolutional neural network auto-encoder unsupervised learning classification 

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

Copyright information

© Springer-Verlag Berlin Heidelberg 2011

Authors and Affiliations

  • Jonathan Masci
    • 1
  • Ueli Meier
    • 1
  • Dan Cireşan
    • 1
  • Jürgen Schmidhuber
    • 1
  1. 1.Istituto Dalle Molle di Studi sull’Intelligenza Artificiale (IDSIA)LuganoSwitzerland

Personalised recommendations