Login| Sign Up| Help| Contact|

Patent Searching and Data


Title:
MODEL LEARNING DEVICE, MODEL LEARNING METHOD, AND PROGRAM
Document Type and Number:
WIPO Patent Application WO/2019/194128
Kind Code:
A1
Abstract:
Provided is a model learning feature with which it is possible, without impairing the performance of a model learned using the data of a given domain, to additionally learn using the data of another domain. The present invention includes: a setup unit for generating a mask from a learned model parameter that is the initial value of a model parameter Ω; a feature quantity processing unit for calculating an output probability distribution that is the distribution of probability that an output corresponding to a feature quantity extracted from input data in a domain different from the domain used in the learning of the learned model parameter is the output of an output number m; and a model learning unit for learning the model parameter Ω using the mask, the output probability distribution, and a correct answer output number that is a number for identifying a correct answer output that corresponds to the feature quantity. The model learning unit calculates an update difference δ(ω) for an element ω of the model parameter Ω by a prescribed expression in which there are used a loss function L(Ω) and a mask element γ that corresponds to the element ω of the model parameter Ω, and updates the element ω.

Inventors:
MORIYA TAKAFUMI (JP)
YAMAGUCHI YOSHIKAZU (JP)
Application Number:
PCT/JP2019/014476
Publication Date:
October 10, 2019
Filing Date:
April 01, 2019
Export Citation:
Click for automatic bibliography generation   Help
Assignee:
NIPPON TELEGRAPH & TELEPHONE (JP)
International Classes:
G06N20/00; G06N3/08
Foreign References:
JP2012128744A2012-07-05
Other References:
TOKUI, SEIYA: "Deep learning approach from the viewpoint of optimization", COMMUNICATIONS OF THE OPERATIONS RESEARCH SOCIETY OF JAPAN, vol. 60, no. 4, 1 April 2015 (2015-04-01), pages 191 - 197, ISSN: 0030-3674
Attorney, Agent or Firm:
NAKAO, Naoki et al. (JP)
Download PDF: