The patent badge is an abbreviated version of the USPTO patent document. The patent badge does contain a link to the full patent document.

The patent badge is an abbreviated version of the USPTO patent document. The patent badge covers the following: Patent number, Date patent was issued, Date patent was filed, Title of the patent, Applicant, Inventor, Assignee, Attorney firm, Primary examiner, Assistant examiner, CPCs, and Abstract. The patent badge does contain a link to the full patent document (in Adobe Acrobat format, aka pdf). To download or print any patent click here.

Date of Patent:
May. 21, 2019

Filed:

Sep. 01, 2016
Applicant:

Fujitsu Limited, Kawasaki-shi, Kanagawa, JP;

Inventors:

Li Chen, Beijing, CN;

Song Wang, Beijing, CN;

Wei Fan, Beijing, CN;

Jun Sun, Beijing, CN;

Naoi Satoshi, Kawasaki, JP;

Assignee:

FUJITSU LIMITED, Kawasaki, JP;

Attorney:
Primary Examiner:
Int. Cl.
CPC ...
G06K 9/62 (2006.01); G06T 5/20 (2006.01); G06N 3/08 (2006.01);
U.S. Cl.
CPC ...
G06K 9/6232 (2013.01); G06K 9/6255 (2013.01); G06K 9/6256 (2013.01); G06N 3/08 (2013.01); G06T 5/20 (2013.01); G06T 2207/10004 (2013.01); G06T 2207/20084 (2013.01);
Abstract

A training method and a training apparatus for a neutral network for image recognition are provided. The method includes: representing a sample image as a point set in a high-dimensional space, a size of the high-dimensional space being a size of space domain of the sample image multiplied by a size of intensity domain of the sample image; generating a first random perturbation matrix having a same size as the high-dimensional space; smoothing the first random perturbation matrix; perturbing the point set in the high-dimensional space using the smoothed first random perturbation matrix to obtain a perturbed point set; and training the neutral network using the perturbed point set as a new sample. With the training method and the training apparatus, classification performance of a conventional convolutional neural network is improved, thereby generating more training samples, reducing influence of overfitting, and enhancing generalization performance of the convolutional neural network.


Find Patent Forward Citations

Chen, Li. (2019). Training method and apparatus for neural network for image recognition (U.S. Patent No. 10296813). U.S. Patent and Trademark Office. https://idiyas.com/patent/badge/10296813

Data source: USPTO (United States Patent and Trademark Office) public patent records. Weekly synchronization. How IDiyas builds this profile

Loading…