Compound and Parallel Modes of Tropical Convolutional Neural Networks
This work addresses computational efficiency for deep learning practitioners, but it appears incremental as it builds on existing tropical CNNs with new variants.
The authors tackled the problem of high computational costs in deep convolutional neural networks by proposing compound and parallel tropical convolutional neural networks (cTCNN and pTCNN) that use tropical min-plus and max-plus kernels to reduce multiplications, and experiments showed these variants match or exceed the performance of other CNN methods on various datasets.
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.