公开(公告)号：US20250086922A1

公开(公告)日：2025-03-13

申请号：US18243612

申请日：2023-09-07

Applicant: NVIDIA Corporation

Inventor： David Jesus Acuna Marrero ,  Rafid Mahmood ,  James Robert Lucas ,  Yuan-Hong Liao ,  Sanja Fidler

IPC: G06V10/25 ,  G06V10/82 ,  G06V20/70

Abstract: Apparatuses, system, and techniques use one or more neural networks to generate a modified bounding box based, at least in part, on one or more second bounding boxes.

公开(公告)号：US20230385687A1

公开(公告)日：2023-11-30

申请号：US17828663

申请日：2022-05-31

Applicant: NVIDIA Corporation

Inventor： Rafid Reza Mahmood ,  James Robert Lucas ,  David Jesus Acuna Marrero ,  Daiqing Li ,  Jonah Philion ,  Jose Manuel Alvarez Lopez ,  Zhiding Yu ,  Sanja Fidler ,  Marc Law

IPC: G06N20/00 ,  G06K9/62

CPC classification number: G06N20/00 ,  G06K9/6265

Abstract: Approaches for training data set size estimation for machine learning model systems and applications are described. Examples include a machine learning model training system that estimates target data requirements for training a machine learning model, given an approximate relationship between training data set size and model performance using one or more validation score estimation functions. To derive a validation score estimation function, a regression data set is generated from training data, and subsets of the regression data set are used to train the machine learning model. A validation score is computed for the subsets and used to compute regression function parameters to curve fit the selected regression function to the training data set. The validation score estimation function is then solved for and provides an output of an estimate of the number additional training samples needed for the validation score estimation function to meet or exceed a target validation score.

公开(公告)号：US20240126811A1

公开(公告)日：2024-04-18

申请号：US18098015

申请日：2023-01-17

Applicant: NVIDIA Corporation

Inventor： Marc Teva Law ,  James Robert Lucas

IPC: G06F16/901

CPC classification number: G06F16/9024

Abstract: Apparatuses, systems, and techniques to indicate data dependencies. In at least one embodiment, one or more neural networks are used to generate one or more indicators of one or more data dependencies and one or more indicators of direction of the one or more data dependencies.

公开(公告)号：US20230376849A1

公开(公告)日：2023-11-23

申请号：US18318212

申请日：2023-05-16

Applicant: NVIDIA Corporation

Inventor： Rafid Reza Mahmood ,  Marc Law ,  James Robert Lucas ,  Zhiding Yu ,  Jose Manuel Alvarez Lopez ,  Sanja Fidler

IPC: G06N20/00

CPC classification number: G06N20/00

Abstract: In various examples, estimating optimal training data set sizes for machine learning model systems and applications. Systems and methods are disclosed that estimate an amount of data to include in a training data set, where the training data set is then used to train one or more machine learning models to reach a target validation performance. To estimate the amount of training data, subsets of an initial training data set may be used to train the machine learning model(s) in order to determine estimates for the minimum amount of training data needed to train the machine learning model(s) to reach the target validation performance. The estimates may then be used to generate one or more functions, such as a cumulative density function and/or a probability density function, wherein the function(s) is then used to estimate the amount of training data needed to train the machine learning model(s).

公开(公告)号：US20250111201A1

公开(公告)日：2025-04-03

申请号：US18477184

申请日：2023-09-28

Applicant: Nvidia Corporation

Inventor： James Robert Lucas ,  Derek Lim ,  Haggai Maron ,  Marc Teva Law

IPC: G06N3/0455 ,  G06N3/08

Abstract: Embodiments are disclosed for a generating graph representations of neural networks to be used as input for one or more metanetworks. Architectural information can be extracted from a neural network and used to generate graph a representation. A subgraph can be generated for each layer of the neural network, where each subgraph includes nodes that correspond to neurons and connecting edges that correspond to weights. Each layer of the neural network can be associated with a bias node that is connected to individual nodes of that layer using edges representing bias weights. Various types of neural networks and layers of neural networks can be represented by such graphs, which are then used as inputs for metanetworks. The subgraphs can be combined into a comprehensive graph representation of the neural network, which can be provided as input to a metanetwork to generate network parameters or perform another such operation.

公开(公告)号：US20250029334A1

公开(公告)日：2025-01-23

申请号：US18356588

申请日：2023-07-21

Applicant: Nvidia Corporation

Inventor： Xingguang Yan ,  Or Perel ,  James Robert Lucas ,  Towaki Takikawa ,  Karsten Julian Kreis ,  Maria Shugrina ,  Sanja Fidler ,  Or Litany

IPC: G06T17/20 ,  G06T3/40

Abstract: Approaches presented herein provide systems and methods for generating three-dimensional (3D) objects using compressed data as an input. One or more models may learn from a hash table of latent features to map different features to a reconstruction domain, using a hash function as part of a learned process. A 3D shape for an object may be encoded to a multi-layered grid and represented by a series of embeddings, where given point within the grid may be interpolated based on the embeddings for a given layer of the multi-layered grid. A decoder may then be trained to use the embeddings to generate an output object.