Fast classifier learning under bounded computational resources using Partitioned Restricted Boltzmann Machines
Hasari Tosun, John W. Sheppard · 2016
We develop a Partitioned Restricted Boltzmann Machine (PRBM) for classification. We demonstrate that this method provides both speed and accuracy. Specifically, because it is partitioned into smaller RBMs, all available data can be used for training, and individual RBMs can be trained in parallel. Moreover, as the number of dimensions increases, the number of partitions can be increased to significantly reduce runtime computational resource requirements. All other recently developed methods using RBMs for classification suffer from some serious disadvantage under bounded computational resources; one is forced to either use a subsample of the whole data, run fewer iterations (early stop criterion), or both. Our Partitioned-RBM method provides an innovative scheme to overcome this shortcoming.