公开(公告)号：US20220036179A1

公开(公告)日：2022-02-03

申请号：US16945753

申请日：2020-07-31

Applicant: NVIDIA CORPORATION

Inventor： Animesh GARG ,  Hongyu REN ,  Yuke ZHU ,  Anima ANANDKUMAR

IPC: G06N3/08 ,  G06N5/04 ,  G06N3/04

Abstract: One embodiment of a method for performing a task includes generating a first posterior distribution of a global latent context variable for the task based on a pool of contexts sampled from one or more previous episodes of the task. The method also includes generating a second posterior distribution of a local latent context variable for a current time step in a current episode of the task based on one or more recent contexts sampled at one or more previous time steps of the current episode. The method further includes causing an agent to perform an action related to carrying out the task based on the first posterior distribution, the second posterior distribution, and a current state associated with the current time step.

公开(公告)号：US20250078489A1

公开(公告)日：2025-03-06

申请号：US18542423

申请日：2023-12-15

Applicant: NVIDIA CORPORATION

Inventor： Bingyin ZHAO ,  Jose Manuel ALVAREZ LOPEZ ,  Anima ANANDKUMAR ,  Shi Yi LAN ,  Zhiding YU

IPC: G06V10/82 ,  G06V10/77

Abstract: One embodiment of the present invention sets forth a technique for training an image classifier. The technique includes training a first vision transformer model to generate patch labels for corresponding images patches of images, converting the patch labels to token labels, and training a second vision transformer model to classify images based on the token labels.

公开(公告)号：US20240013504A1

公开(公告)日：2024-01-11

申请号：US17977884

申请日：2022-10-31

Applicant: NVIDIA CORPORATION

Inventor： Zhiding YU ,  Boyi LI ,  Chaowei XIAO ,  De-An HUANG ,  Weili NIE ,  Linxi FAN ,  Anima ANANDKUMAR

IPC: G06V10/26 ,  G06V10/774 ,  G06V10/77 ,  G06V10/80 ,  G06F40/284

CPC classification number: G06V10/26 ,  G06V10/774 ,  G06V10/7715 ,  G06V10/80 ,  G06F40/284

Abstract: One embodiment of a method for training a machine learning model includes receiving a training data set that includes at least one image, text referring to at least one object included in the at least one image, and at least one bounding box annotation associated with the at least one object, and performing, based on the training data set, one or more operations to generate a trained machine learning model to segment images based on text, where the one or more operations to generate the trained machine learning model include minimizing a loss function that comprises at least one of a multiple instance learning loss term or an energy loss term