-
公开(公告)号：US11461644B2
公开(公告)日：2022-10-04
申请号：US16682976
申请日：2019-11-13
Applicant: D-WAVE SYSTEMS INC.
Inventor： Arash Vahdat , Mostafa S. Ibrahim , William G. Macready
Abstract: Fully-supervised semantic segmentation machine learning models are augmented by ancillary machine learning models which generate high-detail predictions from low-detail, weakly-supervised data. The combined model can be trained over both fully- and weakly-supervised data. Only the primary model is required for inference, post-training. The combined model can be made self-correcting during training by adjusting the ancillary model's output based on parameters learned over both the fully- and weakly-supervised data. The self-correction module may combine the output of the primary and ancillary models in various ways, including through linear combinations and via neural networks. The self-correction module and ancillary model may benefit from disclosed pre-training techniques.
-
公开(公告)号：US11164050B2
公开(公告)日：2021-11-02
申请号：US15822884
申请日：2017-11-27
Applicant: D-Wave Systems Inc.
Inventor： Arash Vahdat
Abstract: Machine learning classification models which are robust against label noise are provided. Noise may be modelled explicitly by modelling “label flips”, where incorrect binary labels are “flipped” relative to their ground truth value. Distributions of label flips may be modelled as prior and posterior distributions in a flexible architecture for machine learning systems. An arbitrary classification model may be provided within the system. The classification model is made more robust to label noise by operation of the prior and posterior distributions. Particular prior and approximating posterior distributions are disclosed.
-
Patent Agency Ranking
公开(公告)号：US11625612B2
公开(公告)日：2023-04-11
申请号：US16779035
申请日：2020-01-31
Applicant: D-WAVE SYSTEMS INC.
Inventor： Arash Vahdat , Mani Ranjbar , Mehran Khodabandeh , William G. Macready , Zhengbing Bian
Abstract: The domain adaptation problem is addressed by using the predictions of a trained model over both source and target domain to retain the model with the assistance of an auxiliary model and a modified objective function. Inaccuracy in the model's predictions in the target domain is treated as noise and is reduced by using a robust learning framework during retraining, enabling unsupervised training in the target domain. Applications include object detection models, where noise in retraining is reduced by explicitly representing label noise and geometry noise in the objective function and using the ancillary model to inject information about label noise.
-
公开(公告)号：US20200160175A1
公开(公告)日：2020-05-21
申请号：US16682976
申请日：2019-11-13
Applicant: D-WAVE SYSTEMS INC.
Inventor： Arash Vahdat , Mostafa S. Ibrahim , William G. Macready
Abstract: Fully-supervised semantic segmentation machine learning models are augmented by ancillary machine learning models which generate high-detail predictions from low-detail, weakly-supervised data. The combined model can be trained over both fully- and weakly-supervised data. Only the primary model is required for inference, post-training. The combined model can be made self-correcting during training by adjusting the ancillary model's output based on parameters learned over both the fully- and weakly-supervised data. The self-correction module may combine the output of the primary and ancillary models in various ways, including through linear combinations and via neural networks. The self-correction module and ancillary model may benefit from disclosed pre-training techniques.
-
公开(公告)号：US20180150728A1
公开(公告)日：2018-05-31
申请号：US15822884
申请日：2017-11-27
Applicant: D-Wave Systems Inc.
Inventor： Arash Vahdat
CPC classification number: G06K9/6278 , G06K9/6232 , G06K9/6256 , G06N3/0427 , G06N3/0454 , G06N3/0472 , G06N3/08 , G06N5/04 , G06N7/005
Abstract: Machine learning classification models which are robust against label noise are provided. Noise may be modelled explicitly by modelling “label flips”, where incorrect binary labels are “flipped” relative to their ground truth value. Distributions of label flips may be modelled as prior and posterior distributions in a flexible architecture for machine learning systems. An arbitrary classification model may be provided within the system. The classification model is made more robust to label noise by operation of the prior and posterior distributions. Particular prior and approximating posterior distributions are disclosed.
-
公开(公告)号：US11531852B2
公开(公告)日：2022-12-20
申请号：US15822884
申请日：2017-11-27
Applicant: D-Wave Systems Inc.
Inventor： Arash Vahdat
Abstract: Machine learning classification models which are robust against label noise are provided. Noise may be modelled explicitly by modelling “label flips”, where incorrect binary labels are “flipped” relative to their ground truth value. Distributions of label flips may be modelled as prior and posterior distributions in a flexible architecture for machine learning systems. An arbitrary classification model may be provided within the system. The classification model is made more robust to label noise by operation of the prior and posterior distributions. Particular prior and approximating posterior distributions are disclosed.
-
公开(公告)号：US20200257984A1
公开(公告)日：2020-08-13
申请号：US16779035
申请日：2020-01-31
Applicant: D-WAVE SYSTEMS INC.
Inventor： Arash Vahdat , Mani Ranjbar , Mehran Khodabandeh , William G. Macready , Zhengbing Bian
Abstract: The domain adaptation problem is addressed by using the predictions of a trained model over both source and target domain to retain the model with the assistance of an auxiliary model and a modified objective function. Inaccuracy in the model's predictions in the target domain is treated as noise and is reduced by using a robust learning framework during retraining, enabling unsupervised training in the target domain. Applications include object detection models, where noise in retraining is reduced by explicitly representing label noise and geometry noise in the objective function and using the ancillary model to inject information about label noise.
-
-
-
-
-
-
Search Results
7
records
(took 0.028 seconds)
