公开(公告)号：US20250061323A1

公开(公告)日：2025-02-20

申请号：US18367223

申请日：2023-09-12

Applicant: NVIDIA Corporation

Inventor： Vishwesh Nath ,  Daguang Xu ,  Bin Liu ,  Yufan He ,  Sachidanand Alle ,  Pengcheng Ma ,  Raghav Mani ,  Marc Thomas Edgar ,  Andrew Feng

IPC: G06N3/08

Abstract: Apparatuses, systems, and techniques to perform active learning. In at least one embodiment, one or more neural networks are trained using training data selected for manual relabeling based, at least in part, on an amount by which the training data is mis-labeled

公开(公告)号：US20240303504A1

公开(公告)日：2024-09-12

申请号：US18124999

申请日：2023-03-22

Applicant: NVIDIA Corporation

Inventor： Ziyue Xu ,  Holger Reinhard Roth ,  Meirui Jiang ,  Wenqi Li ,  Dong Yang ,  Can Zhao ,  Vishwesh Nath ,  Daguang Xu

IPC: G06N3/098

CPC classification number: G06N3/098

Abstract: Apparatuses, systems, and techniques to train/use one or more neural networks. In at least one embodiment, a processor comprises one or more circuits to cause neural network training information to be aggregated based, at least in part, on contribution of the neural network training data and one or more performance metrics of the neural network.

公开(公告)号：US20230074950A1

公开(公告)日：2023-03-09

申请号：US17410471

申请日：2021-08-24

Applicant: Nvidia Corporation

Inventor： Daguang Xu ,  Xiaosong Wang ,  Lickkong Tam ,  Riddhish Bhalodia ,  Kevin Lu ,  Yuhong Wen ,  Ali Hatmizadeh

IPC: G06K9/00 ,  G06K9/20 ,  G06K9/62

Abstract: Apparatuses, systems, and techniques are presented to detect one or more objects in one or more images. In at least one embodiment, one or more neural networks can be used to detect one or more objects in one or more images based, at least in part, on textual descriptions of the one or more objects.

公开(公告)号：US20220058466A1

公开(公告)日：2022-02-24

申请号：US16998694

申请日：2020-08-20

Applicant: NVIDIA Corporation

Inventor： Dong Yang ,  Wenqi Li ,  Ziyue Xu ,  Xiaosong Wang ,  Can Zhao ,  Holger Reinhard Roth ,  Daguang Xu

IPC: G06N3/04 ,  G06N3/08

Abstract: Apparatuses, systems, and techniques to generate an optimized neural network architecture. In at least one embodiment, various neural network components are used to generate one or more neural network configurations, and each neural network configuration is trained in order to determine an optimal neural network architecture for a training dataset.

公开(公告)号：US20220027672A1

公开(公告)日：2022-01-27

申请号：US16940241

申请日：2020-07-27

Applicant: NVIDIA Corporation

Inventor： Ziyue Xu ,  Xiaosong Wang ,  Dong Yang ,  Holger Reinhard Roth ,  Can Zhao ,  Wentao Zhu ,  Daguang Xu

IPC: G06K9/62 ,  G06K9/34 ,  G06N3/08

Abstract: Apparatuses, systems, and techniques to train one or more neural networks to generate labels for unsupervised or partially-supervised data. In at least one embodiment, one or more pseudolabels are generated by a training framework based on available weak annotations for an input medical image, and combined with feature information about said input medical image generated by one or more neural networks to generate a label about said input medical image.

公开(公告)号：US20210374518A1

公开(公告)日：2021-12-02

申请号：US16885170

申请日：2020-05-27

Applicant: NVIDIA Corporation

Inventor： Wentao Zhu ,  Daguang Xu ,  Can Zhao ,  Ziyue Xu ,  Holger Reinhard Roth

IPC: G06N3/08 ,  G06N3/04 ,  G06F9/38 ,  G06K9/62 ,  G06T7/00 ,  G06T7/10

Abstract: Apparatuses, systems, and techniques are described herein to speed up inferencing in a neural network by copying output from one layer of the neural network to another computing resource based on dependencies among layers in the network. In at least one embodiment, a processor comprising one or more circuits causes two or more subsequent layers of one or more neural networks to be performed on separate computing resources from a previous layer of the one or more neural networks.

公开(公告)号：US20210334955A1

公开(公告)日：2021-10-28

申请号：US16858219

申请日：2020-04-24

Applicant: Nvidia Corporation

Inventor： Holger Roth ,  Dong Yang ,  Daguang Xu ,  Vishwesh Nath

IPC: G06T7/00 ,  G06F40/169 ,  G06N3/08 ,  G06T7/11

Abstract: Apparatuses, systems, and techniques are presented to predict annotations for objects in images. In at least one embodiment, one or more annotations corresponding to one or more objects within one or more images are generated based, at least in part, on one or more neural networks iteratively trained using the one or more images.

公开(公告)号：US11100643B2

公开(公告)日：2021-08-24

申请号：US16568161

申请日：2019-09-11

Applicant: NVIDIA Corporation

Inventor： Dong Yang ,  Holger Reinhard Roth ,  Ziyue Xu ,  Fausto Milletari ,  Ling Zhang ,  Te-Chung Isaac Yang ,  Daguang Xu

IPC: G06T7/10 ,  G06N3/04 ,  G06T5/00 ,  G06T7/00

Abstract: In at least one embodiment, a reinforcement-learning-based searching approach is used to produce a training configuration for a machine-learning model. In at least one embodiment, 3D medical image segmentation is performed using learned image preprocessing parameters.

公开(公告)号：US20200327674A1

公开(公告)日：2020-10-15

申请号：US16380759

申请日：2019-04-10

Applicant: NVIDIA Corporation

Inventor： Dong Yang ,  Daguang Xu ,  Fengze Liu ,  Yingda Xia

IPC: G06T7/12 ,  G06N3/08 ,  G06T7/13 ,  G06T7/60 ,  G06K9/62

Abstract: Comparison logic compares boundaries of features of or more images based, at least in part, on identifying boundaries and indication logic coupled to the comparison logic to indicate whether the boundaries differ by at least a first threshold. The boundaries might comprise a first label mask representing boundaries of objects in an image that are boundaries in a segmentation determined from a segmentation process and a second label mask from a shape evaluation process applied to the first label mask. The indication logic might be configured to compare the first label mask and the second label mask to determine a quality of the segmentation. A neural network might perform the segmentation. Shape evaluation using the first label mask as an input and the second label mask as an output might be performed by a variational autoencoder. A graphical processing unit (GPU) might be used for the segmentation and/or the autoencoder.

公开(公告)号：US12072954B1

公开(公告)日：2024-08-27

申请号：US16676314

申请日：2019-11-06

Applicant: NVIDIA Corporation

Inventor： Wenqi Li ,  Fausto Milletari ,  Daguang Xu ,  Yan Cheng ,  Nicola Christin Rieke ,  Charles Jonathan Hancox ,  Wentao Zhu ,  Rong Ou ,  Andrew Feng

IPC: G06T7/00 ,  G06F7/57 ,  G06F18/214 ,  G06N3/045 ,  G06N3/063 ,  G06N3/08 ,  G06V10/94 ,  G16H30/20

CPC classification number: G06F18/2148 ,  G06F7/57 ,  G06N3/045 ,  G06N3/063 ,  G06N3/08 ,  G06V10/955 ,  G16H30/20 ,  G06V2201/03

Abstract: Apparatuses, systems, and techniques to perform federated training of neural networks while maintaining control over dissemination of local models of neural networks from which aspects of local training data might be extracted. In at least one embodiment, a neural network is trained on local training data and a local model is provided to be aggregated with other local models into a global model that is in turn used for further local model training, wherein a provided local model or training is adjusted to reduce an ability to extract aspects of local training data therefrom.