Restricted Deep Belief Networks for Multi-View Learning
Abstract
Deep belief network (DBN) is a probabilistic generative model with multiple layers of hidden nodes and a layer of visible nodes, where parameterizations between layers obey harmonium or restricted Boltzmann machines (RBMs). In this paper we present restricted deep belief network (RDBN) for multi-view learning, where each layer of hidden nodes is composed of view-specific and shared hidden nodes, in order to learn individual and shared hidden spaces from multiple views of data. View-specific hidden nodes are connected to corresponding view-specific hidden nodes in the lower-layer or visible nodes involving a specific view, whereas shared hidden nodes follow inter-layer connections without restrictions as in standard DBNs. RDBN is trained using layer-wise contrastive divergence learning. Numerical experiments on synthetic and real-world datasets demonstrate the useful behavior of the RDBN, compared to the multi-wing harmonium (MWH) which is a two-layer undirected model.
Cite
Text
Kang and Choi. "Restricted Deep Belief Networks for Multi-View Learning." European Conference on Machine Learning and Principles and Practice of Knowledge Discovery in Databases, 2011. doi:10.1007/978-3-642-23783-6_9Markdown
[Kang and Choi. "Restricted Deep Belief Networks for Multi-View Learning." European Conference on Machine Learning and Principles and Practice of Knowledge Discovery in Databases, 2011.](https://mlanthology.org/ecmlpkdd/2011/kang2011ecmlpkdd-restricted/) doi:10.1007/978-3-642-23783-6_9BibTeX
@inproceedings{kang2011ecmlpkdd-restricted,
title = {{Restricted Deep Belief Networks for Multi-View Learning}},
author = {Kang, Yoonseop and Choi, Seungjin},
booktitle = {European Conference on Machine Learning and Principles and Practice of Knowledge Discovery in Databases},
year = {2011},
pages = {130-145},
doi = {10.1007/978-3-642-23783-6_9},
url = {https://mlanthology.org/ecmlpkdd/2011/kang2011ecmlpkdd-restricted/}
}