首页|'Machine Learning Context Based Confidence Calibration' in Patent Application Ap proval Process (USPTO 20240070516)
'Machine Learning Context Based Confidence Calibration' in Patent Application Ap proval Process (USPTO 20240070516)
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
The following quote was obtained by the news editors from the background informa tion supplied by the inventors: “When a machine learning model is used in a task to draw an inference or make a prediction based on input data, the machine lear ning model will typically also output a confidence score that serves as a relati ve qualification as to how confident the machine learning model is in the infere nce or prediction. For example, a confidence score can be modeled as a decimal n umber between 0 and 1, or a percentage between 0% and 100% . A confidence score approaching 1 (100%) indicates that the machin e learning model is strongly confident in its prediction, while a confidence sco re approaching 0 (0%) indicates that the machine learning model has little confidence in its prediction. A software application can then consider w hether or not to use the prediction from the machine learning model from the con fidence score, for example based on whether the confidence score at least meets a confidence threshold value.”
NETL
NSTL
