公开(公告)号：US20220391778A1

公开(公告)日：2022-12-08

申请号：US17770919

申请日：2019-10-23

Applicant: Google LLC

Inventor： Bradley Ray Green ,  Shawn Ryan O'Banion

IPC: G06N20/20

Abstract: The present disclosure provides for the generation of embeddings within a machine learning framework, such as, for example, a federated learning framework in which a high-quality centralized model is trained on training data distributed over a large number of clients each with unreliable network connections and low computational power. In an example federated learning setting, in each of a plurality of rounds, each client independently updates the model based on its local data and communicates the updated model back to the server, where all the client-side updates are used to update a global model. The present disclosure provides systems and methods that may generate embeddings with local training data while preserving the privacy of a user of the client device.

公开(公告)号：US20230113131A1

公开(公告)日：2023-04-13

申请号：US17909579

申请日：2020-03-05

Applicant: Shawn O'Banion ,  Wenhuan WEI ,  Yukun ZHU ,  Google LLC

Inventor： Shawn Ryan O'Banion ,  Wenhuan Wei ,  Yukun Zhu

IPC: G06V20/70 ,  G06V10/98 ,  G06V10/771 ,  G06V10/75 ,  G06V10/74 ,  G06V10/82

Abstract: The present disclosure is directed to systems and methods for performing automated labeling of images. Labeled images can be used to train machine-learned models to infer image attributes such as quality for suggesting user actions.