專利授權區國立清華大學國際產學營運總中心 Operations Center for Industry Collaboration

搜尋專利授權區

關鍵字

» 新增關鍵字

選單

專利授權區

專利授權區
專利名稱(中)	訓練機器學習模型的方法、裝置和電腦程式產品
專利名稱(英)	METHOD, DEVICE AND COMPUTER PROGRAM PRODUCT FOR TRAINING MACHINE LEARNING MODELS
專利家族	中華民國：I860054 美國：2025-0069590(公開號)
專利權人	國立清華大學 100.00%
發明人	李祈均,吳亞澤
技術領域	通信傳輸,資訊工程,電子電機

專利摘要(中)
本發明提出一種訓練機器學習模型的方法。在所述方法中，根據多個權重從第一訓練集中抽樣，以在第一迭代中訓練機器學習模型。第一訓練集包括對應於多個權重的多個級別。此外，在第一迭代後利用驗證集評估機器學習模型按多個級別的多個第一效能；根據這些第一效能更新每個級別對應的權重；以及根據更新後的這些權重重新從第一訓練集中抽樣，以在第一迭代之後的第二迭代中訓練機器學習模型。此外，使用上述方法的裝置和電腦程序產品亦被提出。

專利摘要(中)

本發明提出一種訓練機器學習模型的方法。在所述方法中，根據多個權重從第一訓練集中抽樣，以在第一迭代中訓練機器學習模型。第一訓練集包括對應於多個權重的多個級別。此外，在第一迭代後利用驗證集評估機器學習模型按多個級別的多個第一效能；根據這些第一效能更新每個級別對應的權重；以及根據更新後的這些權重重新從第一訓練集中抽樣，以在第一迭代之後的第二迭代中訓練機器學習模型。此外，使用上述方法的裝置和電腦程序產品亦被提出。

專利摘要(英)
A method for training a machine learning model is provided. In this method, samples are drawn from a first training set according to multiple weights for training the machine learning model in a first epoch. The first training set includes multiple levels corresponding to the multiple weights. After the first epoch, the machine learning model is evaluated using a validation set for multiple first performances at the multiple levels. Additionally, the weight corresponding to each level are updated based on the first performances, and samples are redrawn from the first training set according to the updated weights for training the machine learning model in a second epoch following the first epoch. Moreover, a device and a computer program product utilizing the above method are also provided.

專利摘要(英)

A method for training a machine learning model is provided. In this method, samples are drawn from a first training set according to multiple weights for training the machine learning model in a first epoch. The first training set includes multiple levels corresponding to the multiple weights. After the first epoch, the machine learning model is evaluated using a validation set for multiple first performances at the multiple levels. Additionally, the weight corresponding to each level are updated based on the first performances, and samples are redrawn from the first training set according to the updated weights for training the machine learning model in a second epoch following the first epoch. Moreover, a device and a computer program product utilizing the above method are also provided.

聯絡資訊
承辦人姓名	李曉琪
承辦人電話	03-5715131 #31061
承辦人Email	hsiaochi@mx.nthu.edu.tw