公开(公告)号：US20210019663A1

公开(公告)日：2021-01-21

申请号：US16512805

申请日：2019-07-16

Applicant: NXP B.V.

Inventor： Nikita VESHCHIKOV ,  Joppe Willem BOS ,  Simon Johann FRIEDBERGER ,  Brian ERMANS

IPC: G06N20/20 ,  G06N5/04 ,  G06F17/18

Abstract: A method for processing information includes transforming first information based on a first function, transforming second information based on a second function, processing the first transformed information using a first machine-learning model to generate a first result, processing the second transformed information using a second machine-learning model to generate a second result, and aggregating the first result and the second result to generate a decision. The first and second information may be the same information. The first function may be different from the second function. The first machine-learning model may be based on a first algorithm, and the second machine-learning algorithm may be based on a second algorithm.

公开(公告)号：US20210264295A1

公开(公告)日：2021-08-26

申请号：US16795774

申请日：2020-02-20

Applicant: NXP B.V.

Inventor： Brian ERMANS ,  Wilhelmus Petrus Adrianus Johannus Michiels ,  Christine van Vredendaal

IPC: G06N5/04 ,  G06N20/00 ,  G06F16/901

Abstract: A method is provided for analyzing a classification in a machine learning model (ML). In the method, the ML model is trained using a training dataset to produce a trained ML model. One or more samples are provided to the trained ML model to produce one or more prediction classifications. A gradient is determined for the one of more samples at a predetermined layer of the trained ML model. The one or more gradients and the one or more prediction classifications for each sample are stored. Also, an intermediate value of the ML model may be stored. Then, a sample is chosen to analyze. A gradient of the sample is determined if the gradient was not already determined when the at least one gradient is determined. Using the at least one gradient, and one or more of a data structure, a predetermined metric, and an intermediate value, the k nearest neighbors to the sample are determined. A report comprising the sample and the k nearest neighbors may be provided for analysis.