Deep reinforcement learning autoencoder with RA-GAN and GAN
Deep learning utilization to optimize block-structured communication systems has attracted tremendous attention from researchers. Nevertheless, owing to the extensive data transmission between the transmitter and the receiver, communication, in this case, is hard to establish and maintain effectivel...
| Main Authors: | , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Universitas Ahmad Dahlan
2022-11-01
|
| Series: | IJAIN (International Journal of Advances in Intelligent Informatics) |
| Subjects: | |
| Online Access: | https://ijain.org/index.php/IJAIN/article/view/896 |
| _version_ | 1797944824236605440 |
|---|---|
| author | Hoang-Sy Nguyen Cong-Danh Huynh |
| author_facet | Hoang-Sy Nguyen Cong-Danh Huynh |
| author_sort | Hoang-Sy Nguyen |
| collection | DOAJ |
| description | Deep learning utilization to optimize block-structured communication systems has attracted tremendous attention from researchers. Nevertheless, owing to the extensive data transmission between the transmitter and the receiver, communication, in this case, is hard to establish and maintain effectively. As a solution for this, we first investigate typical end-to-end learning for a communication system, Generative Adversarial Network (GAN). Then, two problems associated with GAN-based systems, the gradient vanishing and overfitting, are reviewed. Subsequently, a residual aided GAN (RA-GAN) is proposed as means to overcome these problems. In the proposed learning scheme, the residual learning and the regularization method are used to mitigate the gradient vanishing and over-fitting problems. In the proposed learning scheme, the residual learning and the regularization method are used to mitigate the gradient vanishing and over-fitting problems. Finally, the numerical results performed in MATLAB for simulation and Codelabs for training have proven that the RA-GAN scheme has near-optimal performance and outperforms the conventional GAN scheme. Throughout this case study, readers can understand the issues that would occur when deep learning is applied to a communication system and possible approaches to address them. |
| first_indexed | 2024-04-10T20:44:37Z |
| format | Article |
| id | doaj.art-4ca87ed130b943a8bcfd5d4bedb8c3dd |
| institution | Directory Open Access Journal |
| issn | 2442-6571 2548-3161 |
| language | English |
| last_indexed | 2024-04-10T20:44:37Z |
| publishDate | 2022-11-01 |
| publisher | Universitas Ahmad Dahlan |
| record_format | Article |
| series | IJAIN (International Journal of Advances in Intelligent Informatics) |
| spelling | doaj.art-4ca87ed130b943a8bcfd5d4bedb8c3dd2023-01-24T08:52:21ZengUniversitas Ahmad DahlanIJAIN (International Journal of Advances in Intelligent Informatics)2442-65712548-31612022-11-018331332310.26555/ijain.v8i3.896216Deep reinforcement learning autoencoder with RA-GAN and GANHoang-Sy Nguyen0Cong-Danh Huynh1Becamex Business School, Eastern International UniversityThu Dau Mot UniversityDeep learning utilization to optimize block-structured communication systems has attracted tremendous attention from researchers. Nevertheless, owing to the extensive data transmission between the transmitter and the receiver, communication, in this case, is hard to establish and maintain effectively. As a solution for this, we first investigate typical end-to-end learning for a communication system, Generative Adversarial Network (GAN). Then, two problems associated with GAN-based systems, the gradient vanishing and overfitting, are reviewed. Subsequently, a residual aided GAN (RA-GAN) is proposed as means to overcome these problems. In the proposed learning scheme, the residual learning and the regularization method are used to mitigate the gradient vanishing and over-fitting problems. In the proposed learning scheme, the residual learning and the regularization method are used to mitigate the gradient vanishing and over-fitting problems. Finally, the numerical results performed in MATLAB for simulation and Codelabs for training have proven that the RA-GAN scheme has near-optimal performance and outperforms the conventional GAN scheme. Throughout this case study, readers can understand the issues that would occur when deep learning is applied to a communication system and possible approaches to address them.https://ijain.org/index.php/IJAIN/article/view/896artificial neural networkscommunication systemsreinforcementlearning-based trainingchannel models |
| spellingShingle | Hoang-Sy Nguyen Cong-Danh Huynh Deep reinforcement learning autoencoder with RA-GAN and GAN IJAIN (International Journal of Advances in Intelligent Informatics) artificial neural networks communication systems reinforcement learning-based training channel models |
| title | Deep reinforcement learning autoencoder with RA-GAN and GAN |
| title_full | Deep reinforcement learning autoencoder with RA-GAN and GAN |
| title_fullStr | Deep reinforcement learning autoencoder with RA-GAN and GAN |
| title_full_unstemmed | Deep reinforcement learning autoencoder with RA-GAN and GAN |
| title_short | Deep reinforcement learning autoencoder with RA-GAN and GAN |
| title_sort | deep reinforcement learning autoencoder with ra gan and gan |
| topic | artificial neural networks communication systems reinforcement learning-based training channel models |
| url | https://ijain.org/index.php/IJAIN/article/view/896 |
| work_keys_str_mv | AT hoangsynguyen deepreinforcementlearningautoencoderwithraganandgan AT congdanhhuynh deepreinforcementlearningautoencoderwithraganandgan |