公开(公告)号：US20240119307A1

公开(公告)日：2024-04-11

申请号：US18474934

申请日：2023-09-26

Applicant: Google LLC

Inventor： Hong-You Chen ,  Boqing Gong ,  Mingda Zhang ,  Hang Qi ,  Xuhui Jia ,  Li Zhang

IPC: G06N3/098

CPC classification number: G06N3/098

Abstract: The embodiments are directed towards providing personalized federated learning (PFL) models via sharable federated basis models. A model architecture and learning algorithm for PFL models is disclosed. The embodiments learn a set of basis models, which can be combined layer by layer to form a personalized model for each client using specifically learned combination coefficients. The set of basis models are shared with each client of a set of the clients. Thus, the set of basis models is common to each client of the set of clients. However, each client may generate a unique PFL based on their specifically learned combination coefficients. The unique combination of coefficients for each client may be encoded in a separate personalized vector for each of the clients.

公开(公告)号：US20240422369A1

公开(公告)日：2024-12-19

申请号：US18336577

申请日：2023-06-16

Applicant: Google LLC

Inventor： Yilin Wang ,  Miao Yin ,  Qifei Wang ,  Boqing Gong ,  Neil Aylon Charles Birkbeck ,  Balineedu Chowdary Adsumilli

IPC: H04N21/2343 ,  G06T7/00 ,  H04N19/132 ,  H04N21/466 ,  H04N21/485

Abstract: A method for generating, for a video stream of a first spatial resolution and a first temporal resolution, a first reduced quality steam of a second spatial resolution and a second reduced-quality stream of a second temporal resolution. A first subset of STPs is sampled from the first reduced-quality stream and a second subset of STPs is sampled from the second reduced-quality stream. Using a machine learning model (MLM) the STPs are processed to identify a quality score for each quality-representative STPs that are representative of a quality of the video stream. One or more quality-improving actions for the video stream are identified using the quality scores of the quality-representative STPs.

公开(公告)号：US20210383237A1

公开(公告)日：2021-12-09

申请号：US17337812

申请日：2021-06-03

Applicant: Google LLC

Inventor： Mingxing Tan ,  Cihang Xie ,  Boqing Gong ,  Quoc V. Le

IPC: G06N3/08 ,  G06N3/04

Abstract: Generally, the present disclosure is directed to the training of robust neural network models by using smooth activation functions. Systems and methods according to the present disclosure may generate and/or train neural network models with improved robustness without incurring a substantial accuracy penalty and/or increased computational cost, or without any such penalty at all. For instance, in some examples, the accuracy may improve. A smooth activation function may replace an original activation function in a machine-learned model when backpropagating a loss function through the model. Optionally, one activation function may be used in the model at inference time, and a replacement activation function may be used when backpropagating a loss function through the model. The replacement activation function may be used to update learnable parameters of the model and/or to generate adversarial examples for training the model.

公开(公告)号：US20240320493A1

公开(公告)日：2024-09-26

申请号：US18254634

申请日：2021-02-22

Applicant: Ahmet ISCEN ,  Andre Filgueiras de Araujo ,  Boqing Gong ,  Cordelia Luise SCHMID ,  Google LLC

Inventor： Ahmet Iscen ,  Andre Filgueiras de Araujo ,  Boqing Gong ,  Cordelia Luise Schmid

IPC: G06N3/084

CPC classification number: G06N3/084

Abstract: Class-balanced distillation can train recognition models with little to no bias even if the training dataset has a class imbalance. A two stage training process with instance sampling and class-balanced sampling can train the recognition model to recognize both head classes and tail classes. Moreover, one or more teacher classification models can be trained, and the knowledge can be distilled to a student classification model.