公开(公告)号：US20220284582A1

公开(公告)日：2022-09-08

申请号：US17190724

申请日：2021-03-03

Applicant: NVIDIA Corporation

Inventor： Dong Yang ,  Yufan He ,  Holger Reinhard Roth ,  Can Zhao ,  Daguang Xu

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

Abstract: Apparatuses, systems, and techniques to select a neural network using an amount of memory to be used. In at least one embodiment, a processor includes one or more circuits to cause one or more neural networks to be selected from a plurality of neural networks based, at least in part, on an amount of memory to be used by the one oe more neural networks.

公开(公告)号：US20210397943A1

公开(公告)日：2021-12-23

申请号：US16905252

申请日：2020-06-18

Applicant: NVIDIA Corporation

Inventor： Pablo Ribalta ,  Michal Marcinkiewicz ,  Dong Yang ,  Daguang Xu ,  Przemyslaw Miroslaw Strzelczyk

IPC: G06N3/08 ,  G06N3/04

Abstract: Apparatuses, systems, and techniques to train neural networks to perform classification. In at least one embodiment, one or more neural networks are trained to perform classification based on, for example, using one or more compressed representations of one or more class labels, where the one or more compressed representations have fewer bits than a representation of the one or more class labels.

公开(公告)号：US20210374502A1

公开(公告)日：2021-12-02

申请号：US16889652

申请日：2020-06-01

Applicant: NVIDIA Corporation

Inventor： Holger Reinhard Roth ,  Dong Yang ,  Wenqi Li ,  Andriy Myronenko ,  Wentao Zhu ,  Ziyue Xu ,  Xiaosong Wang ,  Daguang Xu

IPC: G06N3/04 ,  G06N3/08 ,  G06T7/10

Abstract: Apparatuses, systems, and techniques to select a nueral network architecture from a plurality of neural networs in a federated learning (FL) settng. In at least one embodiment, a neural network is trained by combining training resutls from different FL computing systesms, where each of the different FL computing systems, for example, trains different portions of the nerual network.

公开(公告)号：US20200293828A1

公开(公告)日：2020-09-17

申请号：US16813673

申请日：2020-03-09

Applicant: NVIDIA Corporation

Inventor： Xiaosong Wang ,  Ziyue Xu ,  Dong Yang ,  Holger Reinhard Roth ,  Andriy Myronenko ,  Daguang Xu ,  Ling Zhang

IPC: G06K9/62 ,  G06N3/063 ,  G06N3/08 ,  G06N3/04 ,  G06K9/00

Abstract: Apparatuses, systems, and techniques to perform training of neural networks using stacked transformed images. In at least one embodiment, a neural network is trained on stacked transformed images and trained neural network is provided to be used for processing images from an unseen domain distinct from a source domain, wherein stacked transformed images are transformed according to transformation aspects related to domain variations.

公开(公告)号：US12164599B1

公开(公告)日：2024-12-10

申请号：US18232202

申请日：2023-08-09

Applicant: NVIDIA Corporation

Inventor： Holger Roth ,  Yingda Xia ,  Dong Yang ,  Daguang Xu

IPC: G06F18/214 ,  G06F9/30 ,  G06F18/211 ,  G06F18/2433 ,  G06N3/045 ,  G06N3/08 ,  G06N5/04 ,  G16H30/40

Abstract: Volumetric quantification can be performed for various parameters of an object represented in volumetric data. Multiple views of the object can be generated, and those views provided to a set of neural networks that can generate inferences in parallel. The inferences from the different networks can be used to generate pseudo-labels for the data, for comparison purposes, which enables a co-training loss to be determined for the unlabeled data. The co-training loss can then be used to update the relevant network parameters for the overall data analysis network. If supervised data is also available then the network parameters can further be updated using the supervised loss.

公开(公告)号：US20240161282A1

公开(公告)日：2024-05-16

申请号：US18405932

申请日：2024-01-05

Applicant: NVIDIA Corporation

Inventor： Wentao Zhu ,  Daguang Xu ,  Andriy Myronenko ,  Ziyue Xu

IPC: G06T7/00 ,  G06F30/20 ,  G06N3/08 ,  G06T7/11 ,  G06T7/33

CPC classification number: G06T7/0012 ,  G06F30/20 ,  G06N3/08 ,  G06T7/11 ,  G06T7/344 ,  G06T2207/20081 ,  G06T2207/20084

Abstract: Apparatuses, systems, and techniques to perform registration among images. In at least one embodiment, one or more neural networks are trained to indicate registration of features in common among at least two images by generating a first correspondence by simulating a registration process of registering an image and applying the at least two images and the first correspondence to a neural network to derive a second correspondence of the features in common among the at least two images.

公开(公告)号：US20230021926A1

公开(公告)日：2023-01-26

申请号：US17373309

申请日：2021-07-12

Applicant: NVIDIA Corporation

Inventor： Can Zhao ,  Daguang Xu ,  Holger Reinhard Roth ,  Ziyue Xu ,  Dong Yang ,  Andriy Myronenko ,  Lickkong Tam

IPC: G06T3/40 ,  G06K9/62 ,  G06N3/08 ,  G16H30/20

Abstract: Apparatuses, systems, and techniques to generate one or more images of an object. In at least one embodiment, a technique includes training one or more neural networks to generate one or more images of an object from at least a first image of the object and a second lower-resolution image of the object, where the training includes a comparison of the one or more generated images of the object with the second lower-resolution image of the object.

公开(公告)号：US20230019211A1

公开(公告)日：2023-01-19

申请号：US17364341

申请日：2021-06-30

Applicant: NVIDIA Corporation

Inventor： Xiaosong Wang ,  Ziyue Xu ,  Lickkong Tam ,  Dong Yang ,  Daguang Xu

IPC: G06T7/00 ,  G06T3/40 ,  G06N3/04

Abstract: Apparatuses, systems, and techniques to indicate an extent, to which text corresponds to one or more images. In at least one embodiment, an extent to which text corresponds to one or more images is indicated using one or more neural networks and used to train the one or more neural networks.

公开(公告)号：US20220366220A1

公开(公告)日：2022-11-17

申请号：US17244781

申请日：2021-04-29

Applicant: NVIDIA Corporation

Inventor： Holger Reinhard Roth ,  Yingda Xia ,  Daguang Xu ,  Andriy Myronenko ,  Wenqi Li ,  Dong Yang

IPC: G06N3/04 ,  H04L29/08 ,  G06K9/62

Abstract: Apparatuses, systems, and techniques to improve federated learning for neural networks. In at least one embodiment, a federated server dynamically selects neural network weights according to one or more learnable aggregation weights indicating a contribution from each of one or more edge devices or clients during federated training according to various characteristics of each edge device or client model and training data.

公开(公告)号：US20200027210A1

公开(公告)日：2020-01-23

申请号：US16515890

申请日：2019-07-18

Applicant: NVIDIA Corporation

Inventor： Nicholas Haemel ,  Bojan Vukojevic ,  Risto Haukioja ,  Andrew Feng ,  Yan Cheng ,  Sachidanand Alle ,  Daguang Xu ,  Holger Reinhard Roth ,  Johnny Israeli

IPC: G06T7/00 ,  G16H30/20 ,  G06T19/00 ,  G06N5/04 ,  G06N3/04 ,  G06T7/10 ,  G06F9/455 ,  G06F9/54 ,  G06T5/00

Abstract: In various examples, a virtualized computing platform for advanced computing operations—including image reconstruction, segmentation, processing, analysis, visualization, and deep learning—may be provided. The platform may allow for inference pipeline customization by selecting, organizing, and adapting constructs of task containers for local, on-premises implementation. Within the task containers, machine learning models generated off-premises may be leveraged and updated for location specific implementation to perform image processing operations. As a result, and using the virtualized computing platform, facilities such as hospitals and clinics may more seamlessly train, deploy, and integrate machine learning models within a production environment for providing informative and actionable medical information to practitioners.