Title:
COLLABORATIVE ACTIVATION FOR DEEP LEARNING FIELD
Document Type and Number:
WIPO Patent Application WO/2018/152741
Kind Code:
A1
Abstract:
Methods and apparatus, including computer program products, are provided for machine learning including deep convolutional neural networks. In some example embodiments, there may be provided a method that includes receiving, at a trained machine learning model, a portion of a test image; activating, at the machine learning model, a convolutional result formed based on the portion of the test image, the activation based on neighboring regions in the test image; and providing, by the machine learning model, an activated output. Related systems, methods, and articles of manufacture are also described.
Inventors:
LI HONGYANG (CN)
Application Number:
PCT/CN2017/074576
Publication Date:
August 30, 2018
Filing Date:
February 23, 2017
Export Citation:
Assignee:
NOKIA TECHNOLOGIES OY (FI)
NOKIA TECH BEIJING CO LTD (CN)
NOKIA TECH BEIJING CO LTD (CN)
International Classes:
G06V10/25; G06V10/36; G06V10/764; G06V10/774
Foreign References:
| CN105184309A | 2015-12-23 | |||
| CN106250915A | 2016-12-21 | |||
| CN104537393A | 2015-04-22 | |||
| US20160358321A1 | 2016-12-08 |
Other References:
BLOT, MICHAEL ET AL.: "MAX-MIN CONVOLUTIONAL NEURAL NETWORKS FOR IMAGE CLASSIFICATION", IEEE INTERNATIONAL CONFERENCE ON IMAGE PROCESSING (ICIP 2016), 25 September 2016 (2016-09-25) - 28 September 2016 (2016-09-28), pages 3678 - 3682, XP055536301
Attorney, Agent or Firm:
KING & WOOD MALLESONS (CN)
Download PDF:
Previous Patent: SENSING UNIT
Next Patent: MULTIPLE SURFACES FOR PHYSICAL-TO-IMAGE/IMAGE-TO-PHYSICAL REGISTRATION AND IMAGE VERIFICATION
Next Patent: MULTIPLE SURFACES FOR PHYSICAL-TO-IMAGE/IMAGE-TO-PHYSICAL REGISTRATION AND IMAGE VERIFICATION