Patent · US Active

Training a neural network using stochastic whitening batch normalization

US12182685B2 · kind B2 · utility

0Cited by
0References
16Claims
0Family size

Assignee

Inventors

Key dates

Filing dateJan 16, 2021
Grant dateDec 31, 2024
Priority date
Expiry dateOct 22, 2043

Classification

  • Technology area (CPC G)Physics
  • CPC primaryG06N3/09
  • WIPO fieldComputer technology
  • WIPO sectorElectrical engineering

Abstract

A neural network system, comprising: instructions for implementing at least a SWBN layer in a neural network, and wherein the instructions perform operations comprising: during training of the neural network system on a plurality of batches of training data and for each of the plurality of batches: obtaining a respective first layer output for each of the plurality of training data; determining a plurality of normalization statistics for the batch from the first layer outputs; generating a respective normalized output for each training data in the batch; updating the whitening matrix by a covariance matrix; performing stochastic whitening on the normalized components of each first layer output; transforming the whitened data for each training data; generating a respective SWBN layer output for each of the training data from the transformed whitened data for each training data in the batch; and providing the SWBN layer output.

Source: USPTO / EPO open patent data. Objective bibliographic and citation counts.