You are here

Improving Uncertainty Estimation with Neural Graphical Models

Award Information
Agency: Department of Defense
Branch: National Geospatial-Intelligence Agency
Contract: HM047618C0056
Agency Tracking Number: NGA-P1-18-07
Amount: $99,934.00
Phase: Phase I
Program: SBIR
Solicitation Topic Code: NGA181-005
Solicitation Number: 2018.1
Solicitation Year: 2018
Award Year: 2018
Award Start Date (Proposal Award Date): 2018-09-06
Award End Date (Contract End Date): 2019-06-15
Small Business Information
5266 Hollister Avenue
Santa Barbara, CA 93111
United States
DUNS: 097607852
HUBZone Owned: No
Woman Owned: No
Socially and Economically Disadvantaged: No
Principal Investigator
 Jason Bunk
 (805) 967-9828
Business Contact
 B.S. Manjunath
Phone: (805) 448-8227
Research Institution

Building interpretable, composable autonomous systems requires consideration of uncertainties in the decisions and detections theygenerate. Human analysts need accurate absolute measures of probability to determine how to interpret and use the sometimes noisy resultsof machine learning systems; and composable autonomous systems need to be able to propagate uncertainties so that later reasoningsystems, or humans in the loop, can take them into consideration. For the task of detecting and labeling object groupings, we propose tocombine recent developments in graphical modeling using neural message passing and a comprehensive consideration of statistical sources ofuncertainty using recent developments in Bayesian variational inference for neural networks. Our system can make use of manually specifiedaggregation rules such as the linearity of a group of detections, and can learn unspecified aggregation rules of arbitrary complexity by its use ofdeep neural networks. Our system is also highly interpretable since it provides more than one measure of confidence, quantifying differentaspects of statistical certainty.

* Information listed above is at the time of submission. *

US Flag An Official Website of the United States Government