用于增强深度学习的残差 Kolmogorov-Arnold 网络
Residual Kolmogorov-Arnold Network for Enhanced Deep Learning
AI总结：
本文提出即插即用的残差 Kolmogorov-Arnold 网络（RKAN）模块，通过紧凑的多项式特征变换增强传统卷积网络，在多个视觉任务和基准上一致提升性能并缓解小数据集过拟合与梯度爆炸问题。
摘要：
尽管深度卷积神经网络（CNNs）取得了巨大成功，但由于网络深度中包含数百层，它们可能难以优化且训练成本高昂。传统卷积操作本质上受限于其线性特性和固定激活函数，因此需要许多层来学习数据中有意义的模式。由于这些网络规模庞大，这种方法在计算上效率低下，并且存在过拟合或梯度爆炸的风险，尤其是在小数据集上。因此，我们引入了一个“即插即用”模块，称为残差 Kolmogorov-Arnold 网络（RKAN）。我们的模块非常紧凑，因此可以轻松添加到传统深度网络的任何阶段（层级）中，在其中学习将支持性多项式特征变换集成到现有的卷积框架中。RKAN 在不同的视觉任务和广泛测试的基准上相比基线模型提供了一致的改进，并在这些任务上取得了前沿性能。
英文摘要：
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.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
