Patent · US Active

Method, apparatus and computer program for generating robust automatic learning systems and testing trained automatic learning systems

US11676025B2 · kind B2 · utility

2Cited by

0References

12Claims

0Family size

Assignees

Robert Bosch GmbH · DE
CARNEGIE MELLON UNIVERSITY · US

Inventors

Jeremy Kolter · Pittsburgh, US
Eric Wong · Lexington, US
Frank Schmidt · Leonberg, DE
Jan Hendrik Metzen · Hessenhöfe, DE

Key dates

Filing date	Oct 29, 2018
Grant date	Jun 13, 2023
Priority date	—
Expiry date	Apr 14, 2042

Classification

Technology area (CPC G)Physics
CPC primaryG06N3/088
WIPO fieldComputer technology
WIPO sectorElectrical engineering

Abstract

A method for training an automated learning system includes processing training input with a first neural network and processing the output of the first neural network with a second neural network. The input layer of the second neural network corresponding to the output layer of the first neural network. The output layer of the second neural network corresponding to the input layer of the first neural network. An objective function is determined using the output of the second neural network and a predetermined modification magnitude. The objective function is approximated using random Cauchy projections which are propagated through the second neural network.

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