Learning device, inference device, method, and program

A technology of learning device and learning model, applied in the field of deduction device and learning device, which can solve the problems of difficult deep learning and learning parameter setting, etc.

Inactive Publication Date: 2021-01-08
MITSUBISHI ELECTRIC CORP
View PDF4 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, for users who do not have knowledge about neural networks, AI (Artificial Intelligence), etc., it is difficult to properly select a learning model, determine the size of a neural network, etc., and it is difficult to set learning parameters appropriately.
Therefore, deep learning is difficult for such users

Method used

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • Learning device, inference device, method, and program
  • Learning device, inference device, method, and program
  • Learning device, inference device, method, and program

Examples

Experimental program
Comparison scheme
Effect test

Embodiment approach

[0025] The learning derivation device 1000 according to the embodiment automatically determines appropriate learning parameters based on information indicating prerequisites and restrictions on learning specified by the user. Here, the learning parameters include a learning model indicating the structure of the neural network, the size of the neural network, a learning rate, an activation function, a bias value, and the like.

[0026] More specifically, in the embodiment, the learning derivation device 1000 automatically determines the learning model representing the structure of the neural network and the size of the neural network among the learning parameters based on information indicating the prerequisites and constraints related to learning specified by the user. .

[0027] The learning derivation device 1000 selects a learning model, expands or reduces the size of the neural network for the selected learning model, and executes deep learning using a deep neural network ...

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

PUM

No PUM Login to View More

Abstract

This learning device (100) performs learning using a neural network. A learning condition acquisition unit (110) of the learning device (100) acquires learning conditions that indicate learning prerequisites. A model selection unit (150) selects, according to the learning conditions, a learning model that serves as a framework for the structure of the neural network. A model scale determination unit (160) determines, according to the learning conditions, the scale of the neural network with respect to the selected learning model. A learning unit (170) inputs learning data and performs learningin the neural network, which is constituted according to the scale determined for the selected learning model.

Description

technical field [0001] The invention relates to a learning device, a deduction device, a method and a program. Background technique [0002] When deep learning is performed as one of means in machine learning, it is necessary to set learning parameters according to the purpose, characteristics of learning data, and the like. However, for users who do not have knowledge about neural networks, AI (Artificial Intelligence), etc., it is difficult to appropriately select a learning model, determine the size of a neural network, and the like, and it is difficult to appropriately set learning parameters. Therefore, deep learning is difficult for such users. [0003] In the authentication device that performs personal authentication based on written information described in Patent Document 1, personal authentication is performed using a neural network assigned to a category of written information to be recognized. [0004] Patent Document 1: Japanese Patent Laid-Open No. 2002-1755...

Claims

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

Application Information

Patent Timeline
no application Login to View More
Patent Type & AuthorityApplications(China)
IPC IPC(8): G06N3/08
CPCG06N3/08G06N3/063G06F18/285
Inventor松本大作那须督球山利贞
OwnerMITSUBISHI ELECTRIC CORP