公开(公告)号：US20240412106A1

公开(公告)日：2024-12-12

申请号：US18657283

申请日：2024-05-07

Applicant: STMicroelectronics International N.V.

Inventor： He Huang

IPC: G06N20/00

Abstract: A computer-implemented method for generating a classification model includes: obtaining at least one group of learning data, identifying at least one characteristic to be studied of the learning data, extracting a value of each characteristic defined for all learning data, identifying ranges of values for each characteristic from the extracted values, creating a classification table, assigning a class to each cell of the classification table according to a number of occurrences of the learning data of each group according to their extracted value of each characteristic with respect to the ranges of values defined for each studied characteristic, and generating a classification model comprising the classification table.

公开(公告)号：US20240420024A1

公开(公告)日：2024-12-19

申请号：US18657414

申请日：2024-05-07

Applicant: STMicroelectronics International N.V.

Inventor： He Huang

IPC: G06N20/00

Abstract: A method for creating a classification model includes: obtaining at least one group of initial time-series signals associated with at least one initial acquisition parameter, creating at least one group of simulated time-series signals from the at least one group of initial time-series signals, creating various test classification models, from groups of initial or simulated time-series signals, assessing the performances of each test classification model, obtaining at least one group of final time-series signals associated with at least one final acquisition parameter, and creating the classification model.

公开(公告)号：US20240330774A1

公开(公告)日：2024-10-03

申请号：US18623615

申请日：2024-04-01

Applicant: STMicroelectronics International N.V.

Inventor： He Huang ,  Basile Wolfrom

IPC: G06N20/00

CPC classification number: G06N20/00

Abstract: A computer-implemented method can be used for searching for an optimal hyperparameter combination for defining a machine learning model. The method includes performing tests of hyperparameter combinations. Each test of hyperparameter combination includes a training phase and a test phase. The training phase is adapted to train the machine learning model from training data and the test phase is adapted to calculate a performance score associated with the hyperparameter combination tested from test data. The optimal hyperparameter combination corresponds to the hyperparameter combination having obtained the best performance score among the hyperparameter combinations tested. A weighting coefficient is used for adjusting an amount of training data used for the training phase. The weighting coefficient is dynamically adapted during different tests of the hyperparameter combinations.