A Knowledge Sharing and Individually Guided Evolutionary Algorithm for Multi-Task Optimization Problems
نویسندگان
چکیده
Multi-task optimization (MTO) is a novel emerging evolutionary computation paradigm. It focuses on solving multiple tasks concurrently while improving performance by utilizing similarities among and historical knowledge. To ensure its high performance, it important to choose proper individuals for each task. Most MTO algorithms limit individual one task, which weakens the effects of information exchange. improve efficiency knowledge transfer more suitable learn from other tasks, this work proposes general framework named individually guided multi-task (IMTO). divides evolutions into vertical horizontal ones, fully explored experience execution tasks. By using concept skill membership, with higher ability are selected. Besides, further effect transfer, only inferior selected at generation. The significant advantage IMTO over multifactorial baseline solvers verified via series benchmark studies.
منابع مشابه
A New Evolutionary Algorithm for Multi-objective Optimization Problems
Among the currently successful Evolutionary Multi-Objective Algorithms (MOEAs), elitism and no sharing factor are two common characteristics and have been demonstrated to improve performance significantly. Based on these two principles, two heuristics, with which impressive improvements were showed in single objective optimization, are introduced in a newly designed EMOA in this paper: multi-pa...
متن کاملFitness Sharing for the Direction-guided Evolutionary Algorithm
In evolutionary computation, fitness sharing is a popular technique to handle multi-modal optimization problems, which include many possible local or global solutions. In our previous publication, we proposed a new direction-based evolutionary algorithm, called DEAL. It was shown working effectively on nonlinear optimization problems. In this paper, we extend further DEAL towards the area of mu...
متن کاملA Particle Swarm Optimization Algorithm for Mixed-Variable Nonlinear Problems
Many engineering design problems involve a combination of both continuous anddiscrete variables. However, the number of studies scarcely exceeds a few on mixed-variableproblems. In this research Particle Swarm Optimization (PSO) algorithm is employed to solve mixedvariablenonlinear problems. PSO is an efficient method of dealing with nonlinear and non-convexoptimization problems. In this paper,...
متن کاملApproximation-Guided Evolutionary Multi-Objective Optimization
Multi-objective optimization problems arise frequently in applications but can often only be solved approximately by heuristic approaches. Evolutionary algorithms have been widely used to tackle multi-objective problems. These algorithms use different measures to ensure diversity in the objective space but are not guided by a formal notion of approximation. We present a new framework of an evol...
متن کاملA FAST FUZZY-TUNED MULTI-OBJECTIVE OPTIMIZATION FOR SIZING PROBLEMS
The most recent approaches of multi-objective optimization constitute application of meta-heuristic algorithms for which, parameter tuning is still a challenge. The present work hybridizes swarm intelligence with fuzzy operators to extend crisp values of the main control parameters into especial fuzzy sets that are constructed based on a number of prescribed facts. Such parameter-less particle ...
متن کاملذخیره در منابع من
با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید
ژورنال
عنوان ژورنال: Applied sciences
سال: 2023
ISSN: ['2076-3417']
DOI: https://doi.org/10.3390/app13010602