用新型模块提升深度网络性能，让模型更高效、更稳定。
Residual Kolmogorov-Arnold Network for Enhanced Deep Learning
- 引入可插入的多项式变换模块，替代传统线性卷积
- 在多个视觉任务中实现领先性能，训练更稳定
- 适合追求高效与高精度的深度学习研究者
尽管深度卷积神经网络（CNN）取得了巨大成功，但其数百层的深度导致优化困难且训练成本高昂。传统卷积操作受限于线性特性及固定激活函数，需大量层数才能学习数据中的有效模式。由于网络规模庞大，该方法计算效率低下，并在小数据集上易引发过拟合或梯度爆炸。为此，我们提出一种‘即插即用’模块——残差柯尔莫哥洛夫-阿诺德网络（RKAN）。该模块结构紧凑，可轻松嵌入传统深度网络的任意层级，通过学习支持性的多项式特征变换来增强现有卷积框架。RKAN在多种视觉任务和广泛测试基准上均显著优于基线模型，实现前沿性能。
原文摘要 · Abstract (English)
Despite their immense success, deep convolutional neural networks (CNNs) can be difficult to optimize and costly to train due to hundreds of layers within the network depth. Conventional convolutional operations are fundamentally limited by their linear nature along with fixed activations, where many layers are needed to learn meaningful patterns in data. Because of the sheer size of these networks, this approach is simply computationally inefficient, and poses overfitting or gradient explosion risks, especially in small datasets. As a result, we introduce a "plug-in" module, called Residual Kolmogorov-Arnold Network (RKAN). Our module is highly compact, so it can be easily added into any stage (level) of traditional deep networks, where it learns to integrate supportive polynomial feature transformations to existing convolutional frameworks. RKAN offers consistent improvements over baseline models in different vision tasks and widely tested benchmarks, accomplishing cutting-edge performance on them.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。