Compound and Parallel Modes of Tropical Convolutional Neural Networks
Fuente:
arXiv
Enregistré dans:
| Auteurs principaux: | , , |
|---|---|
| Format: | Preprint |
| Publié: |
2025
|
| Sujets: | |
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866910907456552960 |
|---|---|
| author | Li, Mingbo Liu, Liying Luo, Ye |
| author_facet | Li, Mingbo Liu, Liying Luo, Ye |
| contents | Convolutional neural networks have become increasingly deep and complex, leading to higher computational costs. While tropical convolutional neural networks (TCNNs) reduce multiplications, they underperform compared to standard CNNs. To address this, we propose two new variants - compound TCNN (cTCNN) and parallel TCNN (pTCNN)-that use combinations of tropical min-plus and max-plus kernels to replace traditional convolution kernels. This reduces multiplications and balances efficiency with performance. Experiments on various datasets show that cTCNN and pTCNN match or exceed the performance of other CNN methods. Combining these with conventional CNNs in deeper architectures also improves performance. We are further exploring simplified TCNN architectures that reduce parameters and multiplications with minimal accuracy loss, aiming for efficient and effective models. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2504_06881 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Compound and Parallel Modes of Tropical Convolutional Neural Networks Li, Mingbo Liu, Liying Luo, Ye Computer Vision and Pattern Recognition Artificial Intelligence I.2.6 Convolutional neural networks have become increasingly deep and complex, leading to higher computational costs. While tropical convolutional neural networks (TCNNs) reduce multiplications, they underperform compared to standard CNNs. To address this, we propose two new variants - compound TCNN (cTCNN) and parallel TCNN (pTCNN)-that use combinations of tropical min-plus and max-plus kernels to replace traditional convolution kernels. This reduces multiplications and balances efficiency with performance. Experiments on various datasets show that cTCNN and pTCNN match or exceed the performance of other CNN methods. Combining these with conventional CNNs in deeper architectures also improves performance. We are further exploring simplified TCNN architectures that reduce parameters and multiplications with minimal accuracy loss, aiming for efficient and effective models. |
| title | Compound and Parallel Modes of Tropical Convolutional Neural Networks |
| topic | Computer Vision and Pattern Recognition Artificial Intelligence I.2.6 |
| url | https://arxiv.org/abs/2504.06881 |