Patent · US Active

Effective building block design for deep convolutional neural networks using search

US10776668B2 · kind B2 · utility

3Cited by

2References

19Claims

0Family size

Assignee

Robert Bosch GmbH · DE

Inventors

Jayanta Kumar Dutta · Sunnyvale, US
Jiayi Liu · Xiamen, CN
Unmesh Kurup · Sunnyvale, US
Mohak Shah · Dublin, US

Key dates

Filing date	Dec 7, 2018
Grant date	Sep 15, 2020
Priority date	—
Expiry date	Mar 26, 2039

Classification

Technology area (CPC G)Physics
CPC primaryG06V30/19173
WIPO fieldComputer technology
WIPO sectorElectrical engineering

Abstract

A search framework for finding effective architectural building blocks for deep convolutional neural networks is disclosed. The search framework described herein utilizes a building block which incorporates branch and skip connections. At least some operations of the architecture of the building block are undefined and treated as hyperparameters which can be automatically selected and optimized for a particular task. The search framework uses random search over the reduced search space to generate a building block and repeats the building block multiple times to create a deep convolutional neural network.

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