US Patent Issued on Dec. 16 for "Fast and scalable explanation of model predictions with dynamic gradient estimation" (California Inventors)

ALEXANDRIA, Va., Dec. 16 -- United States Patent no. 12,499,177, issued on Dec. 16.

"Fast and scalable explanation of model predictions with dynamic gradient estimation" was invented by Iman Haji Abolhassani (Mountain View, Calif.) and Alvin Derek Henrick (Dublin, Calif.).

According to the abstract* released by the U.S. Patent & Trademark Office: "A method provides an accurate machine learning model output explanation. A symmetric path from a reference point to an input data point is determined. The symmetric path represents contributions from features in a feature space of a prediction model. The contribution of the intercept is calculated as the machine learning model output value at the reference point in the feature space. The symmetr...