Patents

Search tools Text Classification Chemistry Measure Numbers Full documents Title Abstract Claims All Any Exact Not Add AND condition These CPCs and their children These exact CPCs Add AND condition
Exact Exact Batch Similar Substructure Substructure (SMARTS) Full documents Claims only Add AND condition Add AND condition
Application Numbers Publication Numbers Either Add AND condition
(Method for embedding and clustering depth self-coding based on Sliced-Waserstein);
About 138 results Download Side-by-side
Sort by · Relevance Group by · None Deduplicate by · Family Results / page · 10

Process to learn new image classes without labels

US US11625557B2 Heiko Hoffmann Hrl Laboratories, Llc

Priority 2018-10-29 • Filed 2020-10-26 • Granted 2023-04-11 • Published 2023-04-11

Described is a system for learning object labels for control of an autonomous platform. Pseudo-task optimization is performed to identify an optimal pseudo-task for each source model of one or more source models. An initial target network is trained using the optimal pseudo-task. Source image …

Systems and methods for few-shot transfer learning

WO EP US CN US20200130177A1 Soheil Kolouri Hrl Laboratories, Llc

Priority 2018-10-29 • Filed 2019-08-05 • Published 2020-04-30

A method for training a controller to control a robotic system includes: receiving a neural network of an original controller for the robotic system based on origin data samples from an origin domain and labels in a label space, the neural network including encoder and classifier parameters, the …

Systems and methods for techniques to process, analyze and model interactive …

US US20230320642A1 Baihan Lin The Trustees Of Columbia University In The City Of New York

Priority 2022-04-08 • Filed 2023-04-05 • Published 2023-10-12

Disclosed are methods, systems, and other implementations for processing, analyzing, and modelling psychotherapy data. The implementations include a method for analyzing psychotherapy data that includes obtaining transcript data representative of spoken dialog in one or more psychotherapy sessions …

Computer implemented method for generating a 3d object

WO EP US GB US20240135259A1 Richard AHLFELD Monolith Ai Limited

Priority 2021-06-17 • Filed 2023-12-18 • Published 2024-04-25

There is provided a method for a computer implemented method for generating a 3D object. The method comprises training a machine learning system to learn design parameter values that give rise to an optimally performing version of the 3D object; and processing, using the machine learning system, …

Differential privacy dataset generation using generative models

US CN DE US11847538B2 Tianshi Cao Nvidia Corporation

Priority 2020-10-02 • Filed 2021-05-11 • Granted 2023-12-19 • Published 2023-12-19

Apparatuses, systems, and techniques to train a generative model based at least in part on a private dataset. In at least one embodiment, the generative model is trained based at least in part on a differentially private Sinkhorn algorithm, for example, using backpropagation with gradient descent …

Artificial intelligence engine architecture for generating candidate drugs

WO EP US CN US11462304B2 Francis Lee Peptilogics, Inc.

Priority 2020-02-12 • Filed 2021-06-04 • Granted 2022-10-04 • Published 2022-10-04

An artificial intelligence engine architecture for generating candidate drugs is disclosed. In one embodiment, a method includes generating, via a creator module, a candidate drug compound including a sequence of a candidate drug compound, including the candidate drug compound as a node in a …

Video prediction using one or more neural networks

WO US CN DE GB US11902705B2 Kevin Shih Nvidia Corporation

Priority 2019-09-03 • Filed 2019-09-03 • Granted 2024-02-13 • Published 2024-02-13

Apparatuses, systems, and techniques to enhance video are disclosed. In at least one embodiment, one or more neural networks are used to create, from a first video, a second video having one or more additional video frames.

Denoising diffusion generative adversarial networks

US US12333688B2 Zhisheng Xiao Nvidia Corporation

Priority 2021-09-30 • Filed 2022-09-30 • Granted 2025-06-17 • Published 2025-06-17

Apparatuses, systems, and techniques are presented to train and utilize one or more neural networks. A denoising diffusion generative adversarial network (denoising diffusion GAN) reduces a number of denoising steps during a reverse process. The denoising diffusion GAN does not assume a Gaussian …

Machine learning model scaling system with energy efficient network data …

US CN DE US12417260B2 Daniel J. Cummings Intel Corporation

Priority 2021-10-20 • Filed 2021-10-20 • Granted 2025-09-16 • Published 2025-09-16

The present disclosure is related to machine learning model swap (MLMS) framework for that selects and interchanges machine learning (ML) models in an energy and communication efficient way while adapting the ML models to real time changes in system constraints. The MLMS framework includes an ML …

Federated learning optimizations

WO EP US WO2021247448A1 Ravikumar Balakrishnan Intel Corporation

Priority 2020-06-01 • Filed 2021-05-29 • Published 2021-12-09

The apparatus of an edge computing node, a system, a method and a machine-readable medium. The apparatus includes a processor to cause an initial set of weights for a global machine learning (ML) model to be transmitted a set of client compute nodes of the edge computing network; process Hessians …
Next
About 138 results