RunPool: A Dynamic Pooling Layer for Convolution Neural Network
Deep learning (DL) has achieved a significant performance in computer vision problems, mainly in automatic feature extraction and representation. However, it is not easy to determine the best pooling method in a different case study. For instance, experts can implement the best types of pooling in i...
| Main Authors: | , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Springer
2020-01-01
|
| Series: | International Journal of Computational Intelligence Systems |
| Subjects: | |
| Online Access: | https://www.atlantis-press.com/article/125932844/view |
| _version_ | 1828827468613550080 |
|---|---|
| author | Huang Jin Jie Putra Wanda |
| author_facet | Huang Jin Jie Putra Wanda |
| author_sort | Huang Jin Jie |
| collection | DOAJ |
| description | Deep learning (DL) has achieved a significant performance in computer vision problems, mainly in automatic feature extraction and representation. However, it is not easy to determine the best pooling method in a different case study. For instance, experts can implement the best types of pooling in image processing cases, which might not be optimal for various tasks. Thus, it is required to keep in line with the philosophy of DL. In dynamic neural network architecture, it is not practically possible to find a proper pooling technique for the layers. It is the primary reason why various pooling cannot be applied in the dynamic and multidimensional dataset. To deal with the limitations, it needs to construct an optimal pooling method as a better option than max pooling and average pooling. Therefore, we introduce a dynamic pooling layer called RunPool to train the convolutional neural network (CNN) architecture. RunPool pooling is proposed to regularize the neural network that replaces the deterministic pooling functions. In the final section, we test the proposed pooling layer to address classification problems with online social network (OSN) dataset. |
| first_indexed | 2024-12-12T15:01:24Z |
| format | Article |
| id | doaj.art-bdd12834fccc476eaaf5f10b56e149d7 |
| institution | Directory Open Access Journal |
| issn | 1875-6883 |
| language | English |
| last_indexed | 2024-12-12T15:01:24Z |
| publishDate | 2020-01-01 |
| publisher | Springer |
| record_format | Article |
| series | International Journal of Computational Intelligence Systems |
| spelling | doaj.art-bdd12834fccc476eaaf5f10b56e149d72022-12-22T00:20:48ZengSpringerInternational Journal of Computational Intelligence Systems1875-68832020-01-0113110.2991/ijcis.d.200120.002RunPool: A Dynamic Pooling Layer for Convolution Neural NetworkHuang Jin JiePutra WandaDeep learning (DL) has achieved a significant performance in computer vision problems, mainly in automatic feature extraction and representation. However, it is not easy to determine the best pooling method in a different case study. For instance, experts can implement the best types of pooling in image processing cases, which might not be optimal for various tasks. Thus, it is required to keep in line with the philosophy of DL. In dynamic neural network architecture, it is not practically possible to find a proper pooling technique for the layers. It is the primary reason why various pooling cannot be applied in the dynamic and multidimensional dataset. To deal with the limitations, it needs to construct an optimal pooling method as a better option than max pooling and average pooling. Therefore, we introduce a dynamic pooling layer called RunPool to train the convolutional neural network (CNN) architecture. RunPool pooling is proposed to regularize the neural network that replaces the deterministic pooling functions. In the final section, we test the proposed pooling layer to address classification problems with online social network (OSN) dataset.https://www.atlantis-press.com/article/125932844/viewDynamic poolingDeep learningMalicious classificationSocial network |
| spellingShingle | Huang Jin Jie Putra Wanda RunPool: A Dynamic Pooling Layer for Convolution Neural Network International Journal of Computational Intelligence Systems Dynamic pooling Deep learning Malicious classification Social network |
| title | RunPool: A Dynamic Pooling Layer for Convolution Neural Network |
| title_full | RunPool: A Dynamic Pooling Layer for Convolution Neural Network |
| title_fullStr | RunPool: A Dynamic Pooling Layer for Convolution Neural Network |
| title_full_unstemmed | RunPool: A Dynamic Pooling Layer for Convolution Neural Network |
| title_short | RunPool: A Dynamic Pooling Layer for Convolution Neural Network |
| title_sort | runpool a dynamic pooling layer for convolution neural network |
| topic | Dynamic pooling Deep learning Malicious classification Social network |
| url | https://www.atlantis-press.com/article/125932844/view |
| work_keys_str_mv | AT huangjinjie runpooladynamicpoolinglayerforconvolutionneuralnetwork AT putrawanda runpooladynamicpoolinglayerforconvolutionneuralnetwork |