-
1.发明授权公开(公告)号：US11049265B2
公开(公告)日：2021-06-29
申请号：US16406242
申请日：2019-05-08
Applicant: NEC Laboratories America, Inc.
Inventor： Paul Vernaza , Nicholas Rhinehart , Anqi Liu , Kihyuk Sohn
Abstract: Systems and methods for training and evaluating a deep generative model with an architecture consisting of two complementary density estimators are provided. The method includes receiving a probabilistic model of vehicle motion, and training, by a processing device, a first density estimator and a second density estimator jointly based on the probabilistic model of vehicle motion. The first density estimator determines a distribution of outcomes and the second density estimator estimates sample quality. The method also includes identifying by the second density estimator spurious modes in the probabilistic model of vehicle motion. The probabilistic model of vehicle motion is adjusted to eliminate the spurious modes.
-
2.发明申请公开(公告)号：US20190355134A1
公开(公告)日：2019-11-21
申请号：US16406242
申请日：2019-05-08
Applicant: NEC Laboratories America, Inc.
Inventor： Paul Vernaza , Nicholas Rhinehart , Anqi Liu , Kihyuk Sohn
Abstract: Systems and methods for training and evaluating a deep generative model with an architecture consisting of two complementary density estimators are provided. The method includes receiving a probabilistic model of vehicle motion, and training, by a processing device, a first density estimator and a second density estimator jointly based on the probabilistic model of vehicle motion. The first density estimator determines a distribution of outcomes and the second density estimator estimates sample quality. The method also includes identifying by the second density estimator spurious modes in the probabilistic model of vehicle motion. The probabilistic model of vehicle motion is adjusted to eliminate the spurious modes.
-
Search Results
2
records
(took 0.012 seconds)
