Development of a crawler for automatic acquisition of training data using genetic programming

2023 Fiscal Year Final Research Report

• Project/Area Number: 22K21291
• Research Category: Grant-in-Aid for Research Activity Start-up
• Allocation Type: Multi-year Fund
• Review Section: 1001:Information science, computer engineering, and related fields
• Research Institution: Kushiro National College of Technology
• Principal Investigator: AKikawa Motohiro 釧路工業高等専門学校, 創造工学科, 助教 (20967004)
• Project Period (FY): 2022-08-31 – 2024-03-31
• Keywords: 遺伝的プログラミング / 深層学習

Outline of Final Research Achievements

A large amount of training data must be prepared to develop a system composed of deep learning. In this research project, we developed a crawler that automatically acquires training data. The crawler to be developed uses a method called genetic programming, which allows the crawler to evolve.
During the research period, we focused on robot control using genetic programming and research to understand genetic programming itself. we also developed the necessary libraries for crawler developments.

Free Research Field

人工知能

Academic Significance and Societal Importance of the Research Achievements

近年の深層学習研究では、優れた学習データを如何に収集するかが重要なポイントとなっている。進化的に学習データを収集するクローラーの開発を行った。ロボット制御や手法の特性に関する研究成果と作成されたライブラリを用いることで、今後学習データ収集の負荷を軽減することが見込める。