公开(公告)号：US20240330685A1

公开(公告)日：2024-10-03

申请号：US18742494

申请日：2024-06-13

Applicant: Samsung Electronics Co., Ltd.

Inventor： Minyoung KIM ,  Timothy HOSPEDALES ,  Da LI ,  Xu HU

IPC: G06N3/08

CPC classification number: G06N3/08

Abstract: The present application relates to a computer-implemented method for an improved technique for optimising the loss function during deep learning. The method includes receiving a training data set comprising a plurality of data items, initialising weights of at least one neural network layer of the ML model, and training, using an iterative process, the at least one neural network layer of the ML model by inputting, into the at least one neural network layer, the plurality of data items, processing the plurality of data items using the at least one neural network layer and the weights, optimising a loss function of the weights by simultaneously minimising a loss value and a loss sharpness using weights that lie in a neighbourhood having a similar low loss value, wherein the neighbourhood is determined by a geometry of a parameter space defined by the weights of the ML model, and updating the weights of the at least one neural network layer using the optimised loss function.

公开(公告)号：US20250077979A1

公开(公告)日：2025-03-06

申请号：US18952216

申请日：2024-11-19

Applicant: SAMSUNG ELECTRONICS CO., LTD.

Inventor： Da LI ,  Ondrej BOHDAL ,  Timothy HOSPEDALES ,  Xu HU

IPC: G06N20/00 ,  H04L67/04 ,  H04L67/306

Abstract: Broadly speaking, the present techniques generally relate a method and apparatus for on-device personalisation of artificial intelligence models. In particular, the present application relates to a computer-implemented method for performing personalised visual or audio analysis on an electronic device using a trained machine learning, ML, model.

公开(公告)号：US20230316085A1

公开(公告)日：2023-10-05

申请号：US18208009

申请日：2023-06-09

Applicant: SAMSUNG ELECTRONICS CO., LTD.

Inventor： Da LI ,  Jan Stuhmer ,  Timothy Hospedales ,  Xu Hu

IPC: G06N3/088

CPC classification number: G06N3/088

Abstract: Broadly speaking, the present techniques generally relate to a computer-implemented method and apparatus for training a machine learning, ML, model which is locally installed on a device, where the ML model may be used in automatic speech recognition, object recognition or similar applications. Advantageously, the present techniques are suitable for implementation on resource-constrained devices that capture audio signals, such as smartphones and Internet of Things devices.