This is a demo code for the convolutional deep belief network (written by Honglak Lee and Kihyuk Sohn):

(Conference version:) Honglak Lee, Roger Grosse, Rajesh Ranganath, and Andrew Y. Ng. Convolutional deep belief networks for scalable unsupervised learning of hierarchical representations. In Proceedings of the 26th International Conference on Machine Learning (ICML), 2009.

(Journal version:) Honglak Lee, Roger Grosse, Rajesh Ranganath, and Andrew Y. Ng. Unsupervised Learning of Hierarchical Representations with Convolutional Deep Belief Networks. Communications of the ACM, vol. 54, no. 10, pp. 95-103, 2011.

For demo, run "demo_cdbn.m" in matlab.

If you find this code useful in your work, please cite one of the following papers:

@inproceedings{Lee+etal09:convDBN,
    title = {Convolutional Deep Belief Networks for Scalable Unsupervised Learning of Hierarchical Representations},
    author = {Lee, Honglak and Grosse, Roger and Ranganath, Rajesh and Ng, Andrew Y.},
    booktitle = {Proceedings of the 26th International Conference on Machine Learning},
    year = {2009},
    pages = {609--616},
}


@article{lee2011unsupervised,
    title={Unsupervised learning of hierarchical representations with convolutional deep belief networks},
    author={Honglak Lee and Roger Grosse and Rajesh Ranganath and A.~Y. Ng},
    journal={Communications of the ACM},
    volume={54},
    number={10},
    pages={95--103},
    year={2011},
    publisher={ACM}
}

NOTE: This code includes the following datasets:

1. Subset of Caltech 101 images available from: www.vision.caltech.edu/Image_Datasets/Caltech101/

2. Natural images from Olshausen's sparse net webpage: http:https://redwood.berkeley.edu/bruno/sparsenet/

If you use these datasets in your work, you should cite the above data sources.