Print Email Facebook Twitter Matrix Product Operator Restricted Boltzmann Machines Title Matrix Product Operator Restricted Boltzmann Machines Author Chen, Cong (The University of Hong Kong) Batselier, K. (TU Delft Team Jan-Willem van Wingerden; The University of Hong Kong) Ko, Ching Yun (The University of Hong Kong) Wong, Ngai (The University of Hong Kong) Date 2019 Abstract A restricted Boltzmann machine (RBM) learns a probability distribution over its input samples and has numerous uses like dimensionality reduction, classification and generative modeling. Conventional RBMs accept vectorized data that dismiss potentially important structural information in the original tensor (multi-way) input. Matrix-variate and tensor-variate RBMs, named MvRBM and TvRBM, have been proposed but are all restrictive by model construction and have weak model expression power. This work presents the matrix product operator RBM (MPORBM) that utilizes a tensor network generalization of Mv/TvRBM, preserves input formats in both the visible and hidden layers, and results in higher expressive power. A novel training algorithm integrating contrastive divergence and an alternating optimization procedure is also developed. Numerical experiments compare the MPORBM with the traditional RBM and MvRBM for data classification and image completion and denoising tasks. The expressive power of the MPORBM as a function of the MPO-rank is also investigated. Subject matrix product operatorsrestricted Boltzmann machinestensors To reference this document use: http://resolver.tudelft.nl/uuid:fa270bb6-b068-4de6-af6d-2d6083384d15 DOI https://doi.org/10.1109/IJCNN.2019.8851877 Publisher IEEE, Piscataway, NJ, USA Embargo date 2020-03-30 ISBN 978-1-7281-2009-6 Source Proceedings of the 2019 International Joint Conference on Neural Networks (IJCNN 2019) Event IJCNN 2019: International Joint Conference on Neural Networks, 2019-07-14 → 2019-07-19, Budapest, Hungary Bibliographical note Green Open Access added to TU Delft Institutional Repository ‘You share, we take care!’ – Taverne project https://www.openaccess.nl/en/you-share-we-take-care Otherwise as indicated in the copyright section: the publisher is the copyright holder of this work and the author uses the Dutch legislation to make this work public. Part of collection Institutional Repository Document type conference paper Rights © 2019 Cong Chen, K. Batselier, Ching Yun Ko, Ngai Wong Files PDF 08851877.pdf 609.53 KB Close viewer /islandora/object/uuid:fa270bb6-b068-4de6-af6d-2d6083384d15/datastream/OBJ/view