19 June 2017 The filling-in function of the Bayesian AutoEncoder Network
Author Affiliations +
Proceedings Volume 10443, Second International Workshop on Pattern Recognition; 104431E (2017) https://doi.org/10.1117/12.2280931
Event: Second International Workshop on Pattern Recognition, 2017, Singapore, Singapore
Abstract
We developed the Bayesian AutoEncoder (BAE) to construct a multi-layer restricted Bayesian Network by extracting features from a training dataset. Networks constructed using BAE have hidden variables that represent features of the data and can execute inferences for each feature. In this paper, we show that a network constructed by BAE can not only recognize features but can also fill in lacking data. We performed experiments and confirmed this filling-in ability.
© (2017) COPYRIGHT Society of Photo-Optical Instrumentation Engineers (SPIE). Downloading of the abstract is permitted for personal use only.
Kaneharu Nishino, Mary Inaba, "The filling-in function of the Bayesian AutoEncoder Network", Proc. SPIE 10443, Second International Workshop on Pattern Recognition, 104431E (19 June 2017); doi: 10.1117/12.2280931; https://doi.org/10.1117/12.2280931
PROCEEDINGS
5 PAGES


SHARE
Back to Top