首页|Researchers Submit Patent Application, 'Detecting and Correcting Anomalies in Co mputer-Based Reasoning Systems', for Approval (USPTO 20240232660)
Researchers Submit Patent Application, 'Detecting and Correcting Anomalies in Co mputer-Based Reasoning Systems', for Approval (USPTO 20240232660)
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:“Many systems are controlled by machine learning systems. A common issue with such systems, however,is that when there is an anomalous out come, such as a system failure, unexpected action, etc., there isno way to know why the system acted in the manner in which it did. For example, in a machine l earningsystem to detect letters or numbers in images, tens or hundreds of thous ands of training data (e.g.,pictures along with coded letters or numbers) might be used to train the system. The system can then beused to act on incoming ima ges to find letters and numbers in those images. At times, those outcomesmight be anomalous. For example, the system may “find” letters or numbers that are not actually in theimages, find incorrect letters or numbers, or fail to find lett ers or numbers in the images.
NETL
NSTL
