MODEL INTERPRETATION

专利名称：MODEL INTERPRETATION

发明人：CHAN, Mark,GILL, Navdeep,HALL, Patrick申请号：US2019/026331申请日：20190408

公开号：WO2019/204072A1公开日：20191024

专利附图：

摘要：Input data associated with a machine learning model is classified into a pluralityof clusters. A plurality of linear surrogate models are generated. One of the plurality oflinear surrogate models corresponds to one of the plurality of clusters. A linear

surrogate model is configured to output a corresponding prediction based on input data

associated with a corresponding cluster. Prediction data associated with the machinelearning model and prediction data associated with the plurality of linear surrogatemodels are outputted.

申请人：H2O.AI INC.

地址：2307 Leghorn Street Mountain View, CA 94043 US

国籍：US

代理人：HWANG, Timothy, H.

更多信息请下载全文后查看