公开(公告)号：US20240095534A1

公开(公告)日：2024-03-21

申请号：US18243348

申请日：2023-09-07

Applicant: NVIDIA Corporation

Inventor： Anima Anandkumar ,  Chaowei Xiao ,  Weili Nie ,  De-An Huang ,  Zhiding Yu ,  Manli Shu

IPC: G06N3/084 ,  G06N3/045

CPC classification number: G06N3/084 ,  G06N3/045

Abstract: Apparatuses, systems, and techniques to perform neural networks. In at least one embodiment, a most consistent output of one or more pre-trained neural networks is to be selected. In at least one embodiment, a most consistent output of one or more pre-trained neural networks is to be selected based, at least in part, on a plurality of variances of one or more inputs to the one or more neural networks.

公开(公告)号：US20240144000A1

公开(公告)日：2024-05-02

申请号：US18307227

申请日：2023-04-26

Applicant: NVIDIA Corporation

Inventor： Yuji Roh ,  Weili Nie ,  De-An Huang ,  Arash Vahdat ,  Animashree Anandkumar

IPC: G06N3/08

CPC classification number: G06N3/08

Abstract: A neural network model is trained for fairness and accuracy using both real and synthesized training data, such as images. During training a first sampling ratio between the real and synthesized training data is optimized. The first sampling ratio may comprise a value for each group (or attribute), where each value is optimized. A second sampling ratio defines relative amounts of training data that are used for each one of the groups. Furthermore, a neural network model accuracy and a fairness metric are both used for updating the first and second sampling ratios during training iterations. The neural network model may be trained using different classes of training data. The second sampling ratio may vary for each class.

公开(公告)号：US20230351807A1

公开(公告)日：2023-11-02

申请号：US17661706

申请日：2022-05-02

Applicant: NVIDIA Corporation

Inventor： Yuzhuo Ren ,  Weili Nie ,  Arash Vahdat ,  Animashree Anandkumar ,  Nishant Puri ,  Niranjan Avadhanam

IPC: G06V40/16 ,  G06V10/82 ,  G06V10/774 ,  G06V10/62

CPC classification number: G06V40/176 ,  G06V10/82 ,  G06V10/774 ,  G06V10/62 ,  G06V40/164

Abstract: A machine learning model (MLM) may be trained and evaluated. Attribute-based performance metrics may be analyzed to identify attributes for which the MLM is performing below a threshold when each are present in a sample. A generative neural network (GNN) may be used to generate samples including compositions of the attributes, and the samples may be used to augment the data used to train the MLM. This may be repeated until one or more criteria are satisfied. In various examples, a temporal sequence of data items, such as frames of a video, may be generated which may form samples of the data set. Sets of attribute values may be determined based on one or more temporal scenarios to be represented in the data set, and one or more GNNs may be used to generate the sequence to depict information corresponding to the attribute values.

公开(公告)号：US20240062534A1

公开(公告)日：2024-02-22

申请号：US17893038

申请日：2022-08-22

Applicant: NVIDIA Corporation

Inventor： Xiaojian Ma ,  Weili Nie ,  Zhiding Yu ,  Huaizu Jiang ,  Chaowei Xiao ,  Yuke Zhu ,  Anima Anandkumar

IPC: G06V10/82 ,  G06V10/20 ,  G06V10/94

CPC classification number: G06V10/82 ,  G06V10/255 ,  G06V10/94

Abstract: A vision transformer (ViT) is a deep learning model that performs one or more vision processing tasks. ViTs may be modified to include a global task that clusters images with the same concept together to produce semantically consistent relational representations, as well as a local task that guides the ViT to discover object-centric semantic correspondence across images. A database of concepts and associated features may be created and used to train the global and local tasks, which may then enable the ViT to perform visual relational reasoning faster, without supervision, and outside of a synthetic domain.

公开(公告)号：US20240029836A1

公开(公告)日：2024-01-25

申请号：US18353773

申请日：2023-07-17

Applicant: NVIDIA Corporation

Inventor： Weili Nie ,  Zichao Wang ,  Chaowei Xiao ,  Animashree Anandkumar

IPC: G16C20/90 ,  G16C20/70

CPC classification number: G16C20/90 ,  G16C20/70

Abstract: A machine learning framework is described for performing generation of candidate molecules for, e.g., drug discovery or other applications. The framework utilizes a pre-trained encoder-decoder model to interface between representations of molecules and embeddings for those molecules in a latent space. A fusion module is located between the encoder and decoder and is used to fuse an embedding for an input molecule with embeddings for one or more exemplary molecules selected from a database that is constructed according to a design criteria. The fused embedding is decoded using the decoder to generate a candidate molecule. The fusion module is trained to reconstruct a nearest neighbor to the input molecule from the database based on the sample of exemplary molecules. An iterative approach may be used during inference to dynamically update the database to include newly generated candidate molecules.

公开(公告)号：US20240412491A1

公开(公告)日：2024-12-12

申请号：US18207953

申请日：2023-06-09

Applicant: NVIDIA Corporation

Inventor： Shagan Sah ,  Nishant Puri ,  Yuzhuo Ren ,  Rajath Bellipady Shetty ,  Weili Nie ,  Arash Vahdat ,  Animashree Anandkumar

IPC: G06V10/776 ,  G06N3/094 ,  G06T11/00 ,  G06V10/75 ,  G06V10/774 ,  G06V10/82 ,  G06V40/16

Abstract: Apparatuses, system, and techniques use one or more first neural networks to generate one or more synthetic data to train one or more second neural networks based, at least in part, on one or more performance metrics of one or more second neural networks.

公开(公告)号：US20230015253A1

公开(公告)日：2023-01-19

申请号：US17505384

申请日：2021-10-19

Applicant: Nvidia Corporation

Inventor： Weili Nie ,  Arash Vahdat ,  Anima Anandkumar

IPC: G06N3/08

Abstract: Apparatuses, systems, and techniques are presented to generate one or more images comprising one or more objects based, at least in part, on one or more dynamically configurable attributes of the one or objects. In at least one embodiment, one or more images comprising one or more objects can be generated based, at least in part, on one or more dynamically configurable attributes of the one or objects.

公开(公告)号：US20220012596A1

公开(公告)日：2022-01-13

申请号：US16925085

申请日：2020-07-09

Applicant: NVIDIA Corporation

Inventor： Weili Nie ,  Tero Tapani Karras ,  Animesh Garg ,  Shoubhik Debnath ,  Anjul Patney ,  Anima Anandkumar

IPC: G06N3/08 ,  G06N3/063 ,  G06N3/04

Abstract: Apparatuses, systems, and techniques used to train one or more neural networks to generate images comprising one or more features. In at least one embodiment, one or more neural networks are trained to determine one or more styles for an input image and then generate features associated with said one or more styles in an output image.

公开(公告)号：US12159694B2

公开(公告)日：2024-12-03

申请号：US18353773

申请日：2023-07-17

Applicant: NVIDIA Corporation

Inventor： Weili Nie ,  Zichao Wang ,  Chaowei Xiao ,  Animashree Anandkumar

IPC: G16C20/00 ,  G06N5/04 ,  G06N7/01 ,  G06N20/00 ,  G06N20/10 ,  G16C20/10 ,  G16C20/30 ,  G16C20/70 ,  G16C20/90

Abstract: A machine learning framework is described for performing generation of candidate molecules for, e.g., drug discovery or other applications. The framework utilizes a pre-trained encoder-decoder model to interface between representations of molecules and embeddings for those molecules in a latent space. A fusion module is located between the encoder and decoder and is used to fuse an embedding for an input molecule with embeddings for one or more exemplary molecules selected from a database that is constructed according to a design criteria. The fused embedding is decoded using the decoder to generate a candidate molecule. The fusion module is trained to reconstruct a nearest neighbor to the input molecule from the database based on the sample of exemplary molecules. An iterative approach may be used during inference to dynamically update the database to include newly generated candidate molecules.

公开(公告)号：US20240273682A1

公开(公告)日：2024-08-15

申请号：US18431527

申请日：2024-02-02

Applicant: NVIDIA Corporation

Inventor： Weili Nie ,  Guan-Horng Liu ,  Arash Vahdat ,  De-An Huang ,  Anima Anandkumar

IPC: G06T5/60 ,  G06T5/50

CPC classification number: G06T5/60 ,  G06T5/50

Abstract: Image restoration generally involves recovering a target clean image from a given image having noise, blurring, or other degraded features. Current image restoration solutions typically include a diffusion model that is trained for image restoration by a forward process that progressively diffuses data to noise, and then by learning in a reverse process to generate the data from the noise. However, the forward process relies on Gaussian noise to diffuse the original data, which has little or no structural information corresponding to the original data versus learning from the degraded image itself which is much more structurally informative compared to the random Gaussian noise. Similar problems also exist for other data-to-data translation tasks. The present disclosure trains a data translation conditional diffusion model from diffusion bridge(s) computed between a first version of the data and a second version of the data, which can yield a model that can provide interpretable generation, sampling efficiency, and reduced processing time.