首页|Researchers Submit Patent Application, 'Device for Clusteringbased Labeling, De vice for Anomaly Detection, and Methods therefor', for Approval (USPTO 202402559 33)
Researchers Submit Patent Application, 'Device for Clusteringbased Labeling, De vice for Anomaly Detection, and Methods therefor', for Approval (USPTO 202402559 33)
扫码查看
点击上方二维码区域，可以放大扫码查看
原文链接
NETL
NSTL
News editors obtained the following quote from the background information suppli ed by the inventors:“In the smart factory field, the number of cases of introdu cing machine learning or deep learning techniquesto improve work efficiency is increasing. As a representative example, manufacturers sometimes introducethis method for the purpose of speeding up and automating the determination of good/d efective products.This conventional method has a limitation in that it requires a data set containing labels to build a machinelearning model to determine goo d/defective products. Even when assuming the case of constructing amodel for an anomaly detection category, it is required to detect data in a normal category and performlabeling. From a manufacturer’s perspective, manual labeling of prod ucts through total inspection maybe a huge burden due to the volume and speed o f products being produced.
NETL
NSTL
