Deep hybrid networks with good out-of-sample object recognition

  title={Deep hybrid networks with good out-of-sample object recognition},
  author={Muhammad Ghifary and W. Kleijn and M. Zhang},
  journal={2014 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)},
We introduce Deep Hybrid Networks that are robust to the recognition of out-of-sample objects, i.e., ones that are drawn from a different probability distribution from the training data distribution. The networks are based on a particular combination of an auto-encoder and stacked Restricted Boltzmann Machines (RBMs). The autoencoder is used to extract sparse features, which are expected to be noise invariant in the observations. The stacked RBMs then observe the sparse features as inputs to… Expand
5 Citations
Domain Generalization for Object Recognition with Multi-task Autoencoders
  • 260
  • PDF
Deep Convolutional Neural Networks and Noisy Images
  • 27
  • PDF
Deep Reconstruction-Classification Networks for Unsupervised Domain Adaptation
  • 407
  • PDF
Conceptual Domain Adaptation Using Deep Learning
  • PDF
Gradual recovery based occluded digit images recognition
  • 1


Measuring Invariances in Deep Networks
  • 373
  • PDF
Stacked Denoising Autoencoders: Learning Useful Representations in a Deep Network with a Local Denoising Criterion
  • 4,784
  • PDF
Sparse Feature Learning for Deep Belief Networks
  • 748
  • Highly Influential
  • PDF
Deep networks for robust visual recognition
  • 94
  • PDF
On optimization methods for deep learning
  • 779
  • PDF
Sparse deep belief net model for visual area V2
  • 980
  • PDF
An investigation of deep neural networks for noise robust speech recognition
  • 570
  • PDF
Exploring Strategies for Training Deep Neural Networks
  • 917
  • PDF
A Fast Learning Algorithm for Deep Belief Nets
  • 11,682
  • Highly Influential
  • PDF
Greedy Layer-Wise Training of Deep Networks
  • 1,503