Unlock instant, AI-driven research and patent intelligence for your innovation.

Multimode multi-objective evolution algorithm based on multi-factor transfer learning

A transfer learning and multi-factor technology, applied in the field of evolutionary computing, can solve problems such as insufficient attention and effective solutions to correlation, and achieve the effects of promoting information transfer, accelerating convergence speed, and improving convergence performance

Pending Publication Date: 2020-09-25
XIAN UNIV OF TECH
View PDF1 Cites 4 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, how to efficiently and effectively mine and utilize the correlation between multi-mode and multi-objective optimization problems has not been fully paid attention to and effectively solved in the existing MMEA.

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
  • Multimode multi-objective evolution algorithm based on multi-factor transfer learning
  • Multimode multi-objective evolution algorithm based on multi-factor transfer learning
  • Multimode multi-objective evolution algorithm based on multi-factor transfer learning

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0045]In order to make the above objects, features and advantages of the present invention more comprehensible, the present invention will be further described in detail below in conjunction with the accompanying drawings and specific embodiments.

[0046] refer to figure 1 , the concrete process of the present invention is as follows:

[0047] Step 1: Initialization: Randomly generate N individuals in the search space as the initial population, use the sorting strategy based on dual space to sort the population, and calculate the scalar fitness value and skill factor of the individual;

[0048] Step 1.1: Initialize the population: Use random key encoding to generate N individuals as the initialization population, P={y 1 ,y 2 ,...y N}, the initial individual dimension is max{D};

[0049] Step 1.2: Initial population evaluation:

[0050] Step 1.2.1: Random key decoding: the random key value in the population will be initialized, according to x i =L i +(U i -L i )×y i ...

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

The embodiment of the invention provides a multimode multi-target evolution algorithm based on multi-factor transfer learning, and relates to the field of evolution calculation. The method comprises the steps of initializing a population, and randomly generating N individuals in a search space to serve as an initial population; propagation: generating offspring individuals for each target vector by adopting a genetic mechanism of model selection and mating, and selectively inheriting skill factors of parent individuals of new individuals by the new individuals; updating and merging the parentpopulation and the child population, and updating scalar fitness values of individuals in the populations; and selection: sorting the merged populations according to individual scalar fitness values to select better individuals to form a next-generation population, and judging whether termination conditions are met or not. And through the special points, information migration between optimizationproblems is realized, so that the optimization problems are subjected to parallel calculation, and the population calculation efficiency is improved.

Description

technical field [0001] The invention relates to the field of evolutionary computing, in particular to a multi-mode and multi-objective evolutionary algorithm for multi-factor migration learning. Background technique [0002] Traditional evolutionary algorithms are usually designed to efficiently solve a single optimization problem at a time. However, in population-based search, there is parallelism between different optimization problems, and there is useful information between related problems that can be used to improve the efficiency of problem solving. efficiency. The idea of ​​multi-factor optimization was inspired in the field of multi-task optimization. In recent years, with the rapid development of machine learning technology, the idea of ​​using the commonalities and differences between different tasks for effective learning has been widely studied; [0003] Jinbo et al. proposed a set of multi-task learning algorithms for collaborative computer-aided diagnosis wit...

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 & Authority Applications(China)
IPC IPC(8): G06N3/12
CPCG06N3/126
Inventor 王彬王丹妮梁怡萍江巧永
Owner XIAN UNIV OF TECH