Restricted Boltzmann Machine with Adaptive Local Hidden Units
Lists
Only you see this
Abstract
Deep belief network (DBN) shows the ability to learn hierarchical feature representation from image datasets which mimics the hierarchical organization of the mammal visual cortex. DBN is composed of a stack of Restricted Boltzmann Machines (RBM) which serves as feature extractors. A number of variants of RBM have been proposed to learn feature representations similar to gabor filters. They require extracting small image patches first. As images vary among different datasets, it is preferable to learn the patch size or a proper region of interest. We propose a variant of RBM with adaptive local hidden units (ALRBM) by adding a distance function to the connection weights between visible and hidden units. Experiments on hand-written digits and human faces show that our algorithm has the ability to learn region-based local feature representations adapting to the content of the images automatically.
BibTeX
@inproceedings{cao2013restricted,
author = {Binbin Cao and Jianmin Li and Jun Wu and Bo Zhang},
title = {{Restricted Boltzmann Machine with Adaptive Local Hidden Units}},
booktitle = {ICONIP},
year = {2013},
doi = {10.1007/978-3-642-42042-9\_39},
}Loading related content...