An Automatic Convolutional Neural Network Optimization Using a Diversity-Guided Genetic Algorithm
Hyperparameters and architecture greatly influence the performance of convolutional neural networks (CNNs); therefore, their optimization is important to obtain the desired results. One of the state-of-the-art methods to achieve this is the use of neuroevolution that utilizes a genetic algorithm (GA...
| Main Authors: | , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IEEE
2021-01-01
|
| Series: | IEEE Access |
| Subjects: | |
| Online Access: | https://ieeexplore.ieee.org/document/9462900/ |
| _version_ | 1818572497613750272 |
|---|---|
| author | Tirana Noor Fatyanosa Masayoshi Aritsugi |
| author_facet | Tirana Noor Fatyanosa Masayoshi Aritsugi |
| author_sort | Tirana Noor Fatyanosa |
| collection | DOAJ |
| description | Hyperparameters and architecture greatly influence the performance of convolutional neural networks (CNNs); therefore, their optimization is important to obtain the desired results. One of the state-of-the-art methods to achieve this is the use of neuroevolution that utilizes a genetic algorithm (GA) to optimize a CNN. However, the GA is often trapped into a local optimum resulting in premature convergence. In this study, we propose an approach called the “diversity-guided genetic algorithm-convolutional neural network (DGGA-CNN)” that uses adaptive parameter control and random injection to facilitate the search process by exploration and exploitation while preserving the population diversity. The alternation between exploration and exploitation is guided by using an average pairwise Hamming distance. Moreover, the DGGA fully handles the architecture of the CNN by using a novel finite state machine (FSM) combined with three novel mutation mechanisms that are specifically created for architecture chromosomes. Tests conducted on suggestion mining and twitter airline datasets reveal that the DGGA-CNN performs well with valid architectures and a comparison with other methods demonstrates its capability and efficiency. |
| first_indexed | 2024-12-14T18:58:00Z |
| format | Article |
| id | doaj.art-09c8b914b3334a53a24faba3692db256 |
| institution | Directory Open Access Journal |
| issn | 2169-3536 |
| language | English |
| last_indexed | 2024-12-14T18:58:00Z |
| publishDate | 2021-01-01 |
| publisher | IEEE |
| record_format | Article |
| series | IEEE Access |
| spelling | doaj.art-09c8b914b3334a53a24faba3692db2562022-12-21T22:51:02ZengIEEEIEEE Access2169-35362021-01-019914109142610.1109/ACCESS.2021.30917299462900An Automatic Convolutional Neural Network Optimization Using a Diversity-Guided Genetic AlgorithmTirana Noor Fatyanosa0https://orcid.org/0000-0002-2801-5947Masayoshi Aritsugi1https://orcid.org/0000-0003-0861-849XGraduate School of Science and Technology, Kumamoto University, Kumamoto, JapanFaculty of Advanced Science and Technology, Kumamoto University, Kumamoto, JapanHyperparameters and architecture greatly influence the performance of convolutional neural networks (CNNs); therefore, their optimization is important to obtain the desired results. One of the state-of-the-art methods to achieve this is the use of neuroevolution that utilizes a genetic algorithm (GA) to optimize a CNN. However, the GA is often trapped into a local optimum resulting in premature convergence. In this study, we propose an approach called the “diversity-guided genetic algorithm-convolutional neural network (DGGA-CNN)” that uses adaptive parameter control and random injection to facilitate the search process by exploration and exploitation while preserving the population diversity. The alternation between exploration and exploitation is guided by using an average pairwise Hamming distance. Moreover, the DGGA fully handles the architecture of the CNN by using a novel finite state machine (FSM) combined with three novel mutation mechanisms that are specifically created for architecture chromosomes. Tests conducted on suggestion mining and twitter airline datasets reveal that the DGGA-CNN performs well with valid architectures and a comparison with other methods demonstrates its capability and efficiency.https://ieeexplore.ieee.org/document/9462900/Convolutional neural networksgenetic algorithmshyperparameter optimizationtext classification |
| spellingShingle | Tirana Noor Fatyanosa Masayoshi Aritsugi An Automatic Convolutional Neural Network Optimization Using a Diversity-Guided Genetic Algorithm IEEE Access Convolutional neural networks genetic algorithms hyperparameter optimization text classification |
| title | An Automatic Convolutional Neural Network Optimization Using a Diversity-Guided Genetic Algorithm |
| title_full | An Automatic Convolutional Neural Network Optimization Using a Diversity-Guided Genetic Algorithm |
| title_fullStr | An Automatic Convolutional Neural Network Optimization Using a Diversity-Guided Genetic Algorithm |
| title_full_unstemmed | An Automatic Convolutional Neural Network Optimization Using a Diversity-Guided Genetic Algorithm |
| title_short | An Automatic Convolutional Neural Network Optimization Using a Diversity-Guided Genetic Algorithm |
| title_sort | automatic convolutional neural network optimization using a diversity guided genetic algorithm |
| topic | Convolutional neural networks genetic algorithms hyperparameter optimization text classification |
| url | https://ieeexplore.ieee.org/document/9462900/ |
| work_keys_str_mv | AT tirananoorfatyanosa anautomaticconvolutionalneuralnetworkoptimizationusingadiversityguidedgeneticalgorithm AT masayoshiaritsugi anautomaticconvolutionalneuralnetworkoptimizationusingadiversityguidedgeneticalgorithm AT tirananoorfatyanosa automaticconvolutionalneuralnetworkoptimizationusingadiversityguidedgeneticalgorithm AT masayoshiaritsugi automaticconvolutionalneuralnetworkoptimizationusingadiversityguidedgeneticalgorithm |