PulseAugur
中
实时 08:27:42
English(EN) Structural Kolmogorov-Arnold Convolutions: Learnable Function on the Values or the Filter Shape as Parameter-Efficient Alternative to Per-Edge Convolutional KANs

新的SKANs提供KANs的参数高效替代方案

作者 PulseAugur 编辑部 · [3 个来源] ·

研究人员引入了结构化Kolmogorov-Arnold卷积（SKANs），作为现有卷积Kolmogorov-Arnold网络（KANs）的一种更参数高效的替代方案。新方法将可学习函数从单个核条目重新定位到卷积的整体结构，作用于像素值或滤波器形状。实验表明，SKAN变体，特别是RF-KAN和SV-KAN，在CIFAR-10和CIFAR-100数据集上取得了具有竞争力的准确率，并且参数数量远少于传统的KANs。 AI

影响 这项研究可能通过减少参数数量同时保持性能，从而实现更高效的深度学习模型。

排序理由 该集群包含一篇详细介绍新模型架构的研究论文。

在 arXiv cs.AI 阅读 →

AI 生成摘要 · Google Gemini · 来自 3 个来源。 我们如何撰写摘要 →

新的SKANs提供KANs的参数高效替代方案

报道来源 [3]

  1. arXiv cs.AI TIER_1 English(EN) · Stefano Mereu, Oleksandr Kuznetsov, Gabriele Marchello, Alessandro Galdelli, Emanuele Frontoni, Adriano Mancini, Ferdinando Cannella ·

    Structural Kolmogorov-Arnold Convolutions: Learnable Function on the Values or the Filter Shape as Parameter-Efficient Alternative to Per-Edge Convolutional KANs

    arXiv:2606.24371v1 Announce Type: cross Abstract: Convolutional Kolmogorov--Arnold Networks (KANs) replace the fixed weights of a convolutional kernel with learnable univariate functions. The dominant formulation attaches one such function to every kernel entry and lets it act on…

  2. arXiv cs.AI TIER_1 English(EN) · Ferdinando Cannella ·

    Structural Kolmogorov-Arnold Convolutions: Learnable Function on the Values or the Filter Shape as Parameter-Efficient Alternative to Per-Edge Convolutional KANs

    Convolutional Kolmogorov--Arnold Networks (KANs) replace the fixed weights of a convolutional kernel with learnable univariate functions. The dominant formulation attaches one such function to every kernel entry and lets it act on pixel values, expressive but parameter-heavy and …

  3. Hugging Face Daily Papers TIER_1 English(EN) ·

    Structural Kolmogorov-Arnold Convolutions: Learnable Function on the Values or the Filter Shape as Parameter-Efficient Alternative to Per-Edge Convolutional KANs

    Convolutional Kolmogorov--Arnold Networks (KANs) replace the fixed weights of a convolutional kernel with learnable univariate functions. The dominant formulation attaches one such function to every kernel entry and lets it act on pixel values, expressive but parameter-heavy and …

相关实体

相关话题