Large-scale deep unsupervised learning using graphics processors

@inproceedings{Raina2009LargescaleDU,
  title={Large-scale deep unsupervised learning using graphics processors},
  author={R. Raina and A. Madhavan and A. Ng},
  booktitle={ICML '09},
  year={2009}
}
  • R. Raina, A. Madhavan, A. Ng
  • Published in ICML '09 2009
  • Computer Science
  • The promise of unsupervised learning methods lies in their potential to use vast amounts of unlabeled data to learn complex, highly nonlinear models with millions of free parameters. We consider two well-known unsupervised learning models, deep belief networks (DBNs) and sparse coding, that have recently been applied to a flurry of machine learning applications (Hinton & Salakhutdinov, 2006; Raina et al., 2007). Unfortunately, current learning algorithms for both models are too slow for large… CONTINUE READING
    Partitioning Large Scale Deep Belief Networks Using Dropout
    Large Scale Distributed Deep Networks
    2314
    Deep Unsupervised Learning on a Desktop PC: A Primer for Cognitive Scientists
    29
    Large-scale restricted boltzmann machines on single GPU
    4
    Deep learning systems as complex networks
    4
    A Large-Scale Architecture for Restricted Boltzmann Machines
    34
    Large-Scale Deep Belief Nets With MapReduce
    49
    Building high-level features using large scale unsupervised learning
    1845

    References

    Publications referenced by this paper.
    SHOWING 1-6 OF 6 REFERENCES
    Reducing the Dimensionality of Data with Neural Networks
    10860
    Large Language Models in Machine Translation
    479
    Automated empirical optimizations of software and the ATLAS project
    1014
    High-performance implementation of the level-3 BLAS
    316
    Automated Empirical Optimization
    139
    Mapreduce for machine learning on multicore. Neural Information Processing Systems
    • 2006