Share Email Print
cover

Proceedings Paper • new

Extremely deep Bayesian learning with Gromov's method
Author(s): Fred Daum; Jim Huang; Arjang Noushin
Format Member Price Non-Member Price
PDF $14.40 $18.00
cover GOOD NEWS! Your organization subscribes to the SPIE Digital Library. You may be able to download this paper for free. Check Access

Paper Abstract

We have invented two new Bayesian deep learning algorithms using stochastic particle flow to compute Bayes’ rule. These learning algorithms have a continuum of layers, in contrast with 10 to 100 discrete layers in standard deep learning neural nets. We compute Bayes’ rule for learning using a stochastic particle flow designed with Gromov’s method. Both deep learning and standard particle filters suffer from the curse of dimensionality, and we mitigate this problem by using stochastic particle flow to compute Bayes’ rule. The intuitive explanation for the dramatic reduction in computational complexity is that stochastic particle flow adaptively moves particles to the correct region of d dimensional space to represent the multivariate probability density of the state vector conditioned on the data. There is nothing analogous to this in standard neural nets (deep or shallow), where the geometry of the network is fixed.

Paper Details

Date Published: 7 May 2019
PDF: 12 pages
Proc. SPIE 11018, Signal Processing, Sensor/Information Fusion, and Target Recognition XXVIII, 110180I (7 May 2019); doi: 10.1117/12.2517980
Show Author Affiliations
Fred Daum, Raytheon Co. (United States)
Jim Huang, Raytheon Co. (United States)
Arjang Noushin, Raytheon Co. (United States)


Published in SPIE Proceedings Vol. 11018:
Signal Processing, Sensor/Information Fusion, and Target Recognition XXVIII
Ivan Kadar; Erik P. Blasch; Lynne L. Grewe, Editor(s)

© SPIE. Terms of Use
Back to Top