论文信息 - Data Normalization in the Learning of Restricted Boltzmann Machines

Data Normalization in the Learning of Restricted Boltzmann Machines

In practice, training Restricted Boltzmann Machines with Contrastive Divergence and other approximate maximum likelihood methods works well on data with black backgrounds. However, when using inverted images for training, learning is typically much worse. In this paper, we propose a very simple yet very eective solution to this problem. The new algorithm requires the

Ilya Sutskever | Yichuan Tang | I. Sutskever

[1] Paul Smolensky,et al. Information processing in dynamical systems: foundations of harmony theory , 1986 .

[2] Geoffrey E. Hinton. Training Products of Experts by Minimizing Contrastive Divergence , 2002, Neural Computation.

[3] Tapani Raiko,et al. Enhanced Gradient and Adaptive Learning Rate for Training Restricted Boltzmann Machines , 2011, ICML.

[4] Klaus-Robert Müller,et al. Efficient BackProp , 2012, Neural Networks: Tricks of the Trade.

[5] Geoffrey E. Hinton. A Practical Guide to Training Restricted Boltzmann Machines , 2012, Neural Networks: Tricks of the Trade.