ReActXGB: A Hybrid Binary Convolutional Neural Network Architecture for Improved Performance and Computational Efficiency
Fuente:
arXiv
Enregistré dans:
| Auteurs principaux: | , |
|---|---|
| Format: | Preprint |
| Publié: |
2024
|
| Sujets: | |
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866910444815384576 |
|---|---|
| author | Chu, Po-Hsun Chen, Ching-Han |
| author_facet | Chu, Po-Hsun Chen, Ching-Han |
| contents | Binary convolutional neural networks (BCNNs) provide a potential solution to reduce the memory requirements and computational costs associated with deep neural networks (DNNs). However, achieving a trade-off between performance and computational resources remains a significant challenge. Furthermore, the fully connected layer of BCNNs has evolved into a significant computational bottleneck. This is mainly due to the conventional practice of excluding the input layer and fully connected layer from binarization to prevent a substantial loss in accuracy. In this paper, we propose a hybrid model named ReActXGB, where we replace the fully convolutional layer of ReActNet-A with XGBoost. This modification targets to narrow the performance gap between BCNNs and real-valued networks while maintaining lower computational costs. Experimental results on the FashionMNIST benchmark demonstrate that ReActXGB outperforms ReActNet-A by 1.47% in top-1 accuracy, along with a reduction of 7.14% in floating-point operations (FLOPs) and 1.02% in model size. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2405_08020 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | ReActXGB: A Hybrid Binary Convolutional Neural Network Architecture for Improved Performance and Computational Efficiency Chu, Po-Hsun Chen, Ching-Han Machine Learning Computer Vision and Pattern Recognition Binary convolutional neural networks (BCNNs) provide a potential solution to reduce the memory requirements and computational costs associated with deep neural networks (DNNs). However, achieving a trade-off between performance and computational resources remains a significant challenge. Furthermore, the fully connected layer of BCNNs has evolved into a significant computational bottleneck. This is mainly due to the conventional practice of excluding the input layer and fully connected layer from binarization to prevent a substantial loss in accuracy. In this paper, we propose a hybrid model named ReActXGB, where we replace the fully convolutional layer of ReActNet-A with XGBoost. This modification targets to narrow the performance gap between BCNNs and real-valued networks while maintaining lower computational costs. Experimental results on the FashionMNIST benchmark demonstrate that ReActXGB outperforms ReActNet-A by 1.47% in top-1 accuracy, along with a reduction of 7.14% in floating-point operations (FLOPs) and 1.02% in model size. |
| title | ReActXGB: A Hybrid Binary Convolutional Neural Network Architecture for Improved Performance and Computational Efficiency |
| topic | Machine Learning Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2405.08020 |