Patent · US Active

System and method for teaching compositionality to convolutional neural networks

US10185914B2 · kind B2 · utility

3Cited by

0References

21Claims

0Family size

Assignee

Vicarious FPC, Inc. · US

Inventors

Austin Charles Stone · San Francisco, US
Huayan Wang · Hauppauge, US
D. Scott Phoenix · Union City, US
Dileep George · Union City, US

Key dates

Filing date	Nov 3, 2017
Grant date	Jan 22, 2019
Priority date	—
Expiry date	Nov 3, 2037

Classification

Technology area (CPC G)Physics
CPC primaryG10L15/16
WIPO fieldComputer technology
WIPO sectorElectrical engineering

Abstract

A system for teaching compositionality to convolutional neural networks includes an unmasked convolutional neural network comprising a first set of convolutional neural network layers; a first masked convolutional neural network comprising a second set of convolutional neural network layers; the unmasked convolutional neural network and the first masked convolutional network sharing convolutional neural network weights; the system training the unmasked and first masked convolutional neural networks simultaneously based on an objective function that seeks to reduce both discriminative loss and compositional loss.

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