The original paper is in English. Non-English content has been machine-translated and may contain typographical errors or mistranslations. ex. Some numerals are expressed as "XNUMX".
Copyrights notice
The original paper is in English. Non-English content has been machine-translated and may contain typographical errors or mistranslations. Copyrights notice
Kami mencadangkan strategi pembelajaran untuk pecutan dalam kelajuan pembelajaran pengaturcaraan genetik (GP), dinamakan struktur hierarki GP (HSGP). HSGP mengeksploitasi berbilang nod pembelajaran (LN) yang disambungkan dalam struktur hierarki, contohnya, pokok binari. Setiap LN menjalankan proses evolusi konvensional untuk mengembangkan populasinya sendiri, dan menghantar populasi berkembang ke LN peringkat lebih tinggi yang bersambung. LN peringkat rendah mengubah populasi dengan subset data latihan yang lebih kecil. LN peringkat lebih tinggi kemudiannya mengintegrasikan populasi berkembang daripada LN peringkat rendah yang disambungkan bersama-sama, dan mengembangkan populasi bersepadu lebih jauh dengan menggunakan subset data latihan yang lebih besar. Dalam HSGP, proses evolusi dilaksanakan secara berurutan daripada LN peringkat bawah ke LN peringkat atas yang berkembang dengan keseluruhan data latihan. Dalam eksperimen, kami mengguna pakai GP konvensional dan HSGP untuk mengembangkan program pengecaman imej untuk imej latihan yang diberikan. Keputusan menunjukkan bahawa penggunaan pembelajaran struktur hierarki boleh meningkatkan kelajuan pembelajaran GP dengan ketara. Untuk mencapai prestasi yang sama, HSGP hanya memerlukan 30-40% daripada kos pengiraan yang diperlukan oleh GP konvensional.
The copyright of the original papers published on this site belongs to IEICE. Unauthorized use of the original or translated papers is prohibited. See IEICE Provisions on Copyright for details.
Salinan
Ukrit WATCHAREERUETAI, Tetsuya MATSUMOTO, Noboru OHNISHI, Hiroaki KUDO, Yoshinori TAKEUCHI, "Acceleration of Genetic Programming by Hierarchical Structure Learning: A Case Study on Image Recognition Program Synthesis" in IEICE TRANSACTIONS on Information,
vol. E92-D, no. 10, pp. 2094-2102, October 2009, doi: 10.1587/transinf.E92.D.2094.
Abstract: We propose a learning strategy for acceleration in learning speed of genetic programming (GP), named hierarchical structure GP (HSGP). The HSGP exploits multiple learning nodes (LNs) which are connected in a hierarchical structure, e.g., a binary tree. Each LN runs conventional evolutionary process to evolve its own population, and sends the evolved population into the connected higher-level LN. The lower-level LN evolves the population with a smaller subset of training data. The higher-level LN then integrates the evolved population from the connected lower-level LNs together, and evolves the integrated population further by using a larger subset of training data. In HSGP, evolutionary processes are sequentially executed from the bottom-level LNs to the top-level LN which evolves with the entire training data. In the experiments, we adopt conventional GPs and the HSGPs to evolve image recognition programs for given training images. The results show that the use of hierarchical structure learning can significantly improve learning speed of GPs. To achieve the same performance, the HSGPs need only 30-40% of the computation cost needed by conventional GPs.
URL: https://global.ieice.org/en_transactions/information/10.1587/transinf.E92.D.2094/_p
Salinan
@ARTICLE{e92-d_10_2094,
author={Ukrit WATCHAREERUETAI, Tetsuya MATSUMOTO, Noboru OHNISHI, Hiroaki KUDO, Yoshinori TAKEUCHI, },
journal={IEICE TRANSACTIONS on Information},
title={Acceleration of Genetic Programming by Hierarchical Structure Learning: A Case Study on Image Recognition Program Synthesis},
year={2009},
volume={E92-D},
number={10},
pages={2094-2102},
abstract={We propose a learning strategy for acceleration in learning speed of genetic programming (GP), named hierarchical structure GP (HSGP). The HSGP exploits multiple learning nodes (LNs) which are connected in a hierarchical structure, e.g., a binary tree. Each LN runs conventional evolutionary process to evolve its own population, and sends the evolved population into the connected higher-level LN. The lower-level LN evolves the population with a smaller subset of training data. The higher-level LN then integrates the evolved population from the connected lower-level LNs together, and evolves the integrated population further by using a larger subset of training data. In HSGP, evolutionary processes are sequentially executed from the bottom-level LNs to the top-level LN which evolves with the entire training data. In the experiments, we adopt conventional GPs and the HSGPs to evolve image recognition programs for given training images. The results show that the use of hierarchical structure learning can significantly improve learning speed of GPs. To achieve the same performance, the HSGPs need only 30-40% of the computation cost needed by conventional GPs.},
keywords={},
doi={10.1587/transinf.E92.D.2094},
ISSN={1745-1361},
month={October},}
Salinan
TY - JOUR
TI - Acceleration of Genetic Programming by Hierarchical Structure Learning: A Case Study on Image Recognition Program Synthesis
T2 - IEICE TRANSACTIONS on Information
SP - 2094
EP - 2102
AU - Ukrit WATCHAREERUETAI
AU - Tetsuya MATSUMOTO
AU - Noboru OHNISHI
AU - Hiroaki KUDO
AU - Yoshinori TAKEUCHI
PY - 2009
DO - 10.1587/transinf.E92.D.2094
JO - IEICE TRANSACTIONS on Information
SN - 1745-1361
VL - E92-D
IS - 10
JA - IEICE TRANSACTIONS on Information
Y1 - October 2009
AB - We propose a learning strategy for acceleration in learning speed of genetic programming (GP), named hierarchical structure GP (HSGP). The HSGP exploits multiple learning nodes (LNs) which are connected in a hierarchical structure, e.g., a binary tree. Each LN runs conventional evolutionary process to evolve its own population, and sends the evolved population into the connected higher-level LN. The lower-level LN evolves the population with a smaller subset of training data. The higher-level LN then integrates the evolved population from the connected lower-level LNs together, and evolves the integrated population further by using a larger subset of training data. In HSGP, evolutionary processes are sequentially executed from the bottom-level LNs to the top-level LN which evolves with the entire training data. In the experiments, we adopt conventional GPs and the HSGPs to evolve image recognition programs for given training images. The results show that the use of hierarchical structure learning can significantly improve learning speed of GPs. To achieve the same performance, the HSGPs need only 30-40% of the computation cost needed by conventional GPs.
ER -