Invention Publication
- Patent Title: DEVICE AND METHOD FOR TRAINING A CLASSIFIER
-
Application No.: EP19212867.6Application Date: 2019-12-02
-
Publication No.: EP3832550A1Publication Date: 2021-06-09
- Inventor: Kolter, Jeremy Zieg , Schmidt, Frank , Fathony, Rizal
- Applicant: Robert Bosch GmbH , Carnegie Mellon University
- Applicant Address: DE 70442 Stuttgart Postfach 30 02 20; US Pittsburgh, PA 15213 5000 Forbes Avenue
- Agency: Bee, Joachim
- Main IPC: G06N3/04
- IPC: G06N3/04 ; G06N3/08
Abstract:
A computer-implemented method for training a classifier (60), particularly a binary classifier, for classifying input signals ( x i ) to optimize performance according to a non-decomposable metric that measures an alignment between classifications ( y i ) corresponding to input signals ( x i ) of a set of training data and corresponding predicted classifications ( ŷ i ) of said input signals obtained from said classifier, comprising the steps of:
- providing weighting factors that characterize how said non-decomposable metric depends on a plurality of terms from a confusion matrix of said classifications ( y i ) and said predicted classifications ( ŷ i );
- training said classifier (60) depending on said provided weighting factors.
- providing weighting factors that characterize how said non-decomposable metric depends on a plurality of terms from a confusion matrix of said classifications ( y i ) and said predicted classifications ( ŷ i );
- training said classifier (60) depending on said provided weighting factors.
Public/Granted literature
- EP3832550B1 DEVICE AND METHOD FOR TRAINING A CLASSIFIER Public/Granted day:2025-02-12
Information query