Asynchronously training machine learning models across client devices for adaptive intelligence

S Choudhary, SK Mishra, A Garg - US Patent 11,593,634, 2023 - Google Patents
2018-06-19 Assigned to ADOBE SYSTEMS INCORPORATED reassignment ADOBE
SYSTEMS INCORPORATED ASSIGNMENT OF ASSIGNORS INTEREST (SEE DOCUMENT …

Distributed labeling for supervised learning

A Bhowmick, RM Rogers, US Vaishampayan… - US Patent …, 2023 - Google Patents
Embodiments described herein provide a technique to crowdsource labeling of training data
for a machine learning model while maintaining the privacy of the data provided by …

Generative adversarial network enriched driving simulation

H Song, J Peng, N Deng, S **ao, T Qin, T Lou… - US Patent …, 2020 - Google Patents
A computer-implemented method and a system for training a computer-based autonomous
driving model used for an autonomous driving operation by an autonomous vehicle are …

Systems and Methods for Deploying and Updating Neural Networks at the Edge of a Network

A Dunne, F Buckley - US Patent App. 16/797,422, 2020 - Google Patents
(2013.01)(57) ABSTRACT Methods, devices and system for updating a neural network on
an edge device that has low-bandwidth uplink capability include a centralized site/device …

Machine learning at edge devices based on distributed feedback

JD Pezzillo, D Burcaw, A Cantarero - US Patent 11,436,527, 2022 - Google Patents
Machine learning (ML) is provided at edge computing devices based on distributed
feedback received from the edge computing devices. A trained instance of an ML model is …

Machine learning model re-training based on distributed feedback

JD Pezzillo, D Burcaw - US Patent 11,494,693, 2022 - Google Patents
Machine learning model re-training based on distributed feedback received from a plurality
of edge computing devices is provided. A trained instance of a machine learning model is …

Systems and methods for providing machine learning model evaluation by using decomposition

DC Merrill, ME Ruberry, O Sayin, B Tunguz… - US Patent …, 2024 - Google Patents
US11960981B2 - Systems and methods for providing machine learning model evaluation by
using decomposition - Google Patents US11960981B2 - Systems and methods for providing …

Systems and methods for model fairness

SJ Kamkar, ME Van Veen, F Li, MF Eberstein… - US Patent …, 2021 - Google Patents
7,711,635 B2 5/2010 Steele et al. 7,765,151 B1 7/2010 Williams et al. 7,813,945 B2 10/2010
Bonissone et al. 7,873,535 B2 1/2011 Umblijs et al. 7,873,570 B2 1/2011 Cagan et al …

Collaborative distributed machine learning

S Wang, T Salonidis - US Patent 11,521,090, 2022 - Google Patents
(57) ABSTRACT A model requester node, which is an edge node of a cloud computing
network, generates a specification of a machine learning model, distributes the specification …

Technique to perform neural network architecture search with federated learning

HR Roth, D Yang, W Li, A Myronenko… - US Patent App. 16 …, 2021 - Google Patents
Apparatuses, systems, and techniques to select a nueral network architecture from a
plurality of neural networs in a federated learning (FL) settng. In at least one embodiment, a …