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：US20240104698A1

公开(公告)日：2024-03-28

申请号：US17719091

申请日：2022-04-12

Applicant: Nvidia Corporation

Inventor： Weili Nie ,  Yujia Huang ,  Chaowei Xiao ,  Arash Vahdat ,  Anima Anandkumar

IPC: G06T5/00 ,  G06N3/04 ,  G06T5/50

CPC classification number: G06T5/002 ,  G06N3/0445 ,  G06N3/0472 ,  G06T5/50 ,  G06T2207/20084

Abstract: Apparatuses, systems, and techniques are presented to remove unintended variations introduced into data. In at least one embodiment, a first image of an object can be generated based, at least in part, upon adding noise to, and removing the noise from, a second image of the object.

公开(公告)号：US20240078423A1

公开(公告)日：2024-03-07

申请号：US17893026

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: G06N3/08 ,  G06F16/55 ,  G06N3/04

CPC classification number: G06N3/08 ,  G06F16/55 ,  G06N3/04

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：US20240028673A1

公开(公告)日：2024-01-25

申请号：US18180476

申请日：2023-03-08

Applicant: NVIDIA Corporation

Inventor： Chaowei Xiao ,  Yolong Cao ,  Danfei Xu ,  Animashree Anandkumar ,  Marco Pavone ,  Xinshuo Weng

IPC: G06F21/14 ,  B60W60/00

CPC classification number: G06F21/14 ,  B60W60/0011

Abstract: In various examples, robust trajectory predictions against adversarial attacks in autonomous machines and applications are described herein. Systems and methods are disclosed that perform adversarial training for trajectory predictions determined using a neural network(s). In order to improve the training, the systems and methods may devise a deterministic attach that creates a deterministic gradient path within a probabilistic model to generate adversarial samples for training. Additionally, the systems and methods may introduce a hybrid objective that interleaves the adversarial training and learning from clean data to anchor the output from the neural network(s) on stable, clean data distribution. Furthermore, the systems and methods may use a domain-specific data augmentation technique that generates diverse, realistic, and dynamically-feasible samples for additional training of the neural network(s).