Title:
LEARNING DEVICE, AND LEARNING METHOD
Document Type and Number:
WIPO Patent Application WO/2019/235636
Kind Code:
A1
Abstract:
A learning device is configured to perform learning by gradient boosting, and includes: data memory units configured to store learning data including a type of feature amount and corresponding gradient information; gradient output units each configured to receive an input of the feature amount and the corresponding gradient information from a corresponding one of the data memory units, and output the gradient information through an output port corresponding to each value of the input feature amount; an addition unit configured to add up one or more pieces of the gradient information corresponding to the same value of the feature amount, and output an added value of the gradient information corresponding to each value of the feature amount; and a histogram memory unit configured to store a histogram obtained by integrating added values of the gradient information corresponding to each value of the feature amount as a bin.
Inventors:
TANAKA TAKUYA (JP)
KASAHARA RYOSUKE (JP)
KASAHARA RYOSUKE (JP)
Application Number:
PCT/JP2019/022834
Publication Date:
December 12, 2019
Filing Date:
June 07, 2019
Export Citation:
Assignee:
RICOH CO LTD (JP)
TANAKA TAKUYA (JP)
KASAHARA RYOSUKE (JP)
TANAKA TAKUYA (JP)
KASAHARA RYOSUKE (JP)
International Classes:
G06N20/00
Domestic Patent References:
| WO2016122636A1 | 2016-08-04 | |||
| WO2018013148A1 | 2018-01-18 |
Foreign References:
| US9098326B1 | 2015-08-04 | |||
| JP2013008270A | 2013-01-10 |
Other References:
MICHAL DROZDZ ET AL: "Abstract", IMAGE PROCESSING & COMMUNICATIONS, vol. 21, no. 3, 1 September 2016 (2016-09-01), pages 27 - 44, XP055604657, DOI: 10.1515/ipc-2016-0014
MICHAL DROZDZTOMASZ KRYJAK: "FPGA Implementation of Multi-scale Face Detection Using HOG Features and SVM Classifier", IMAGE PROCESSING & COMMUNICATIONS, vol. 21.3, 2016, pages 27 - 44
MICHAL DROZDZTOMASZ KRYJAK: "FPGA Implementation of Multi-scale Face Detection Using HOG Features and SVM Classifier", IMAGE PROCESSING & COMMUNICATIONS, vol. 21.3, 2016, pages 27 - 44
Attorney, Agent or Firm:
SAKAI, Hiroaki (JP)
Download PDF:
Previous Patent: COMPOUND, SALT THEREOF AND LIPID PARTICLES
Next Patent: SYRINGE HAVING MOVABLE SYRINGE NEEDLE AND CAMOUFLAGE PAIN POINT NEEDLE
Next Patent: SYRINGE HAVING MOVABLE SYRINGE NEEDLE AND CAMOUFLAGE PAIN POINT NEEDLE