Perception-Distortion Trade-Off with Restricted Boltzmann Machines

Journal Article

In this work, we introduce a new procedure for applying Restricted Boltzmann Machines (RBMs) to missing data inference tasks, based on linearization of the effective energy function governing the distribution of observations. We compare the performance of our proposed procedure with those obtained using existing reconstruction procedures trained on incomplete data. We place these performance comparisons within the context of the perception-distortion trade-off observed in other data reconstruction tasks, which has, until now, remained unexplored in tasks relying on incomplete training data.

Full Text

Duke Authors

Cited Authors

  • Cannella, C; DIng, J; Soltani, M; Zhou, Y; Tarokh, V

Published Date

  • May 1, 2020

Published In

Volume / Issue

  • 2020-May /

Start / End Page

  • 4022 - 4026

International Standard Serial Number (ISSN)

  • 1520-6149

Digital Object Identifier (DOI)

  • 10.1109/ICASSP40776.2020.9052991

Citation Source

  • Scopus