US Patent Application 17738268. TRAINING A NEURAL NETWORK TO ACHIEVE AVERAGE CALIBRATION simplified abstract
Contents
TRAINING A NEURAL NETWORK TO ACHIEVE AVERAGE CALIBRATION
Organization Name
INTERNATIONAL BUSINESS MACHINES CORPORATION
Inventor(s)
Hiroki Yanagisawa of Kawasaki (JP)
Akira Koseki of Kanagawa-ken (JP)
Michiharu Kudo of Kamakura-shi (JP)
TRAINING A NEURAL NETWORK TO ACHIEVE AVERAGE CALIBRATION - A simplified explanation of the abstract
This abstract first appeared for US patent application 17738268 titled 'TRAINING A NEURAL NETWORK TO ACHIEVE AVERAGE CALIBRATION
Simplified Explanation
The patent application describes a method for training a neural network to analyze data in a way that meets average calibration standards.
- The method involves manipulating a data set that includes an outcomes vector and a set of feature vectors.
- The processor repeatedly selects a subset of the feature vectors and generates a distribution vector for the corresponding subset of outcomes.
- A prediction vector is produced by running the neural network on the selected feature vectors.
- The Bregman divergence between the distribution vector and a scoring distribution vector of the prediction vector is calculated.
- The weights of the neural network are updated based on the Bregman divergence.
Original Abstract Submitted
A method, which trains a neural network to perform an analysis that satisfies average calibration, includes a processor manipulating a data set that includes an outcomes vector and a set of feature vectors, each of which corresponds to one of the outcomes in the outcomes vector. The processor repeatedly: selects a subset of the set of feature vectors; generates a distribution vector for a subset of the outcomes vector that corresponds to the subset of the set of feature vectors; produces a prediction vector by running the neural network on the subset of the set of feature vectors; calculates a Bregman divergence between the distribution vector and a scoring distribution vector of the prediction vector; and updates weights of the neural network based on the Bregman divergence.