(aside image)

KyungHyun Cho

M.Sc.,
Postgraduate Researcher in the Deep Learning and Bayesian Modeling
Department of Information and Computer Science,
Aalto University School of Science

Office:
Room A319 in Computer Science Building,
Konemiehentie 2, Otaniemi campus area, Espoo
Postal Address:
Aalto University School of Science,
Department of Information and Computer Science,
P.O. Box 15400, FI-00076 Aalto, Finland
Email:
firstname.lastname@aalto.fi
Google Scholar Profile:
http://scholar.google.fi/citations?user=0RAmmIAAAAAJ

Code

  1. MATLAB Code for Boltzmann Machines and Autoencoders: Download (GitHub)

Publication(s)

Thesis

  1. Cho, KyungHyun. Improved Learning Methods for Restricted Boltzmann Machines. Master's Thesis, Aalto University, 2011. [pdf]

Journals

  1. Cho, K., Raiko, T., and Ilin, A.
    Enhanced Gradient for Training Restricted Boltzmann Machines. [pdf]
    Neural Computation. March 2013.

Conferences

  1. Cho, K., Raiko, T., Ilin, A., and Karhunen, J.
    A Two-stage Pretraining Algorithm for Deep Boltzmann Machines [pdf]
    In Proceedings of the International Conference on Artificial Neural Networks (ICANN 2013).
    Sep 2013. (to appear)
  2. Cho, K.
    Simple Sparsification Improves Sparse Denoising Autoencoders in Denoising Highly Corrupted Images. [pdf]
    In Proceedings of the International Conference on Machine Learning (ICML 2013).
    Jun 2013. (to appear)
  3. Cho, K., Raiko, T., and Ilin, A.
    Gaussian-Bernoulli Deep Boltzmann Machines. [pdf]
    In Proceedings of the International Joint Conference on Neural Networks (IJCNN 2013).
    Aug 2013. (to appear)
  4. Keronen, S., Cho, K., Raiko, T., Ilin, A., and Palomäki, K.
    Gaussian-Bernoulli restricted Boltzmann machines and automatic feature extraction for noise robust missing data mask estimation.
    In Proceedings of the International Conference on Acoustics, Speech, and Signal Processing (ICASSP 2013). May 2013. (to appear)
  5. Cho, K., Ilin, A., and Raiko, T.
    Tikhonov-Type Regularization for Restricted Boltzmann Machines [pdf]
    In Proceedings of the International Conference on Artificial Neural Networks (ICANN 2012). September 2012.
  6. Cho, K. and Reyhani, N.
    An iterative algorithm for singular value decomposition on noisy incomplete matrices. [pdf]
    In Proceedings of the International Joint Conference on Neural Networks (IJCNN 2012). Brisbane, Austraila. June 2012.
  7. Cho, K., Raiko, T., and Ilin, A.
    Enhanced Gradient and Adaptive Learning Rate for Training Restricted Boltzmann Machines. [pdf]
    In Proceedings of the International Conference on Machine Learning (ICML 2011). Bellevue, Washington. June 2011.
  8. Cho, K., Ilin, A., and Raiko, T.
    Improved Learning of Gaussian-Bernoulli Restricted Boltzmann Machines. [pdf]
    In Proceedings of the International Conference on Artificial Neural Networks (ICANN 2011). Espoo, Finland. June 2011.
    Note: The enhanced gradient was used for all the experiments in this paper.
  9. Cho, K., Raiko, T., and Ilin, A.
    Parallel Tempering is Efficient for Learning Restricted Boltzmann Machines. [pdf]
    In Proceedings of the International Joint Conference on Neural Networks (IJCNN 2010). Barcelona, Spain. July 2010.

Workshops

  1. Cho, K., Raiko, T., Ilin, A., and Karhunen, J.
    A Two-stage Pretraining Algorithm for Deep Boltzmann Machines [pdf]
    NIPS 2012 Workshop on Deep Learning and Unsupervised Features Learning. Lake Tahoe, California. Dec 2012.
  2. Cho, K., Raiko, T., and Ilin, A.
    Gaussian-Bernoulli Deep Boltzmann Machines. [pdf]
    NIPS 2011 Workshop on Deep Learning and Unsupervised Features Learning. Granada, Spain. Dec 2011.

Technical Reports and Others

  1. Cho, K.
    Boltzmann Machines and Denoising Autoencoders in Image Denoising. [pdf]
    arXiv e-prints. Jan 2013.
  2. Cho, K., Raiko, T., Karhunen, J.
    Advances in Training Restricted Boltzmann Machines.
    In the 11th Interntional Symposium on Intelligent Data Analysis (IDA 2012). Helsinki, Finland. Oct 2012. (abstract only)
  3. Raiko, T., Cho, K., and Ilin, A.
    Derivations of the Enhanced Gradient for the Boltzmann Machine.
    Technical Report. Aalto University, 2011.
  4. Raiko, T., Cho, K., Ilin, A.
    Enhanced Gradient for Learning Boltzmann Machines.
    In the Learning Workshop. Fort Lauderdale, Florida. April 2011. (abstract only)

Teaching

  1. T-61.3050 Machine Learning: Basic Principles. Teaching Assistant. Autumn, 2012.
  2. T-61.5910 Research Project in Computer and Information Science. Teaching Assistant. 2011 and 2012.