Data Normalization in the Learning of Restricted Boltzmann Machines
Yichuan Tang, Ilya Sutskever · 2011
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