Large-scale deep unsupervised learning using graphics processors

@inproceedings{Raina2009LargescaleDU,
  title={Large-scale deep unsupervised learning using graphics processors},
  author={R. Raina and Anand Madhavan and A. Ng},
  booktitle={ICML '09},
  year={2009}
}
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… Expand
Partitioning Large Scale Deep Belief Networks Using Dropout
Large Scale Distributed Deep Networks
Deep Unsupervised Learning on a Desktop PC: A Primer for Cognitive Scientists
Deep learning systems as complex networks
Large-scale restricted boltzmann machines on single GPU
Large-Scale Deep Belief Nets With MapReduce
A Large-Scale Architecture for Restricted Boltzmann Machines
Building high-level features using large scale unsupervised learning
...
1
2
3
4
5
...

References

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