摘要
以下引文是新闻编辑从新闻编辑提供的背景资料中获得的发明人：“机器学习模型可以使用Tr Aining数据进行训练，其准确度为模型通常与所提供的培训数据的数量和质量成比例。培训数据可作为“对”提供，包括原始数据（例如，图像或其他对象）和一个或多个原始数据表示的标签。这些对用于在模型内形成“连接”，最终，该模型可以根据数据本身预测与新数据相关联的L abel。通常，从手动标记的数据集向机器学习模型提供数据，时间密集。也存在无监督学习方法，但没有人工实验室el来训练机器学习模型，无监督技术往往涉及聚类算法，这可能需要模型改进以提供有意义的群组。
Abstract
The following quote was obtained by the news editors from the background informa tion supplied bythe inventors: “Machine learning models may be trained using tr aining data, with the accuracy of themodels generally proportional to the quant ity and quality of the training data provided. The training datamay be provided as “pairs”, including the raw data (e.g., an image or another object) and one o r morelabels that the raw data represents. These pairs are employed to form “co nnections” within the model,and eventually the model may be able to predict a l abel associated with new data, based on the data itself.Generally, the data are provided to a machine learning model from manually labeled data sets, which istime intensive. Unsupervised learning methods also exist, but without manual lab els to train the machinelearning model, unsupervised techniques tend to involve clustering algorithms, which may demand modelrefinements to provide meaningful clusters.
NETL
NSTL