Extremely deep Bayesian learning with Gromov's method

Fred Daum; Jim Huang; Arjang Noushin

doi:10.1117/12.2517980

7 May 2019 Extremely deep Bayesian learning with Gromov's method

Fred Daum, Jim Huang, Arjang Noushin

Proceedings Volume 11018, Signal Processing, Sensor/Information Fusion, and Target Recognition XXVIII; 110180I (2019) https://doi.org/10.1117/12.2517980
Event: SPIE Defense + Commercial Sensing, 2019, Baltimore, MD, United States

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.

Conference Presentation

Citation Download Citation

Fred Daum, Jim Huang, and Arjang Noushin "Extremely deep Bayesian learning with Gromov's method", Proc. SPIE 11018, Signal Processing, Sensor/Information Fusion, and Target Recognition XXVIII, 110180I (7 May 2019); https://doi.org/10.1117/12.2517980

ACCESS THE FULL ARTICLE

INSTITUTIONAL
Select your institution to access the SPIE Digital Library.

SELECT YOUR INSTITUTION

PERSONAL
Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.

PERSONAL SIGN IN

No SPIE Account? Create one

PURCHASE THIS CONTENT

SUBSCRIBE TO DIGITAL LIBRARY

50 downloads per 1-year subscription

Members: $195

Non-members: $335 ADD TO CART

25 downloads per 1 - year subscription

Members: $145

Non-members: $250 ADD TO CART

PURCHASE SINGLE ARTICLE

Includes PDF, HTML & Video, when available