Title:
COOPERATIVE NEURAL NETWORKS WITH SPATIAL CONTAINMENT CONSTRAINTS
Document Type and Number:
WIPO Patent Application WO/2021/208808
Kind Code:
A1
Abstract:
Methods, systems, and computer program products for cooperative neural networks with spatial containment constraints are provided herein. A computer-implemented method includes dividing a processing task into multiple sub-tasks; training multiple independent neural networks, such that at least some of the multiple sub-tasks correspond to different ones of the multiple independent neural networks; defining, based at least in part on constraint-based domain knowledge related to the processing task, at least one constraint loss for a given one of the multiple sub-tasks, the at least one constraint loss being dependent on output from at least one of the other multiple sub-tasks; and re-training at least a portion of the multiple independent neural networks, the re-training being dependent on using the at least one constraint loss.
Inventors:
WANG XIN RU (US)
ZHENG XINYI (US)
BURDICK DOUGLAS R (US)
KATSIS IOANNIS (US)
ZHENG XINYI (US)
BURDICK DOUGLAS R (US)
KATSIS IOANNIS (US)
Application Number:
PCT/CN2021/086102
Publication Date:
October 21, 2021
Filing Date:
April 09, 2021
Export Citation:
Assignee:
IBM (US)
IBM CHINA CO LTD (CN)
IBM CHINA CO LTD (CN)
International Classes:
G06N3/08
Foreign References:
| US20170286810A1 | 2017-10-05 | |||
| CN109992000A | 2019-07-09 | |||
| CN110866602A | 2020-03-06 | |||
| CN109816107A | 2019-05-28 | |||
| US20190392307A1 | 2019-12-26 |
Attorney, Agent or Firm:
LIU, SHEN & ASSOCIATES (CN)
Download PDF: