We introduce KANICE (Kolmogorov-Arnold Networks with Interactive Convolutional Elements), a novel neural architecture that combines Convolutional Neural Networks (CNNs) with Kolmogorov-Arnold Network (KAN) principles. KANICE integrates Interactive Convolutional Blocks (ICBs) and KAN linear layers into a CNN framework. This leverages KANs' universal approximation capabilities and ICBs' adaptive feature learning. KANICE captures complex, non-linear data relationships while enabling dynamic, context-dependent feature extraction based on the Kolmogorov-Arnold representation theorem. We evaluated KANICE on four datasets: MNIST, Fashion-MNIST, EMNIST, and SVHN, comparing it against standard CNNs, CNN-KAN hybrids, and ICB variants. KANICE consistently outperformed baseline models, achieving 99.35% accuracy on MNIST and 90.05% on the SVHN dataset. Furthermore, we introduce KANICE-mini, a compact variant designed for efficiency. A comprehensive ablation study demonstrates that KANICE-mini achieves comparable performance to KANICE with significantly fewer parameters. KANICE-mini reached 90.00% accuracy on SVHN with 2,337,828 parameters, compared to KANICE's 25,432,000. This study highlights the potential of KAN-based architectures in balancing performance and computational efficiency in image classification tasks. Our work contributes to research in adaptive neural networks, integrates mathematical theorems into deep learning architectures, and explores the trade-offs between model complexity and performance, advancing computer vision and pattern recognition. The source code for this paper is publicly accessible through our GitHub repository (https://github.com/m-ferdaus/kanice).

翻译：我们提出KANICE（具有交互式卷积单元的Kolmogorov-Arnold网络），这是一种将卷积神经网络（CNN）与Kolmogorov-Arnold网络（KAN）原理相结合的新型神经架构。KANICE在CNN框架中集成了交互式卷积块（ICB）与KAN线性层，从而充分利用了KAN的通用逼近能力和ICB的自适应特征学习特性。基于Kolmogorov-Arnold表示定理，KANICE能够捕捉复杂的非线性数据关系，同时实现动态的、上下文相关的特征提取。我们在四个数据集（MNIST、Fashion-MNIST、EMNIST和SVHN）上评估了KANICE，并将其与标准CNN、CNN-KAN混合模型以及ICB变体进行了比较。KANICE在所有基准测试中均优于基线模型，在MNIST上达到99.35%的准确率，在SVHN数据集上达到90.05%。此外，我们提出了KANICE-mini，一种为高效计算设计的紧凑变体。全面的消融实验表明，KANICE-mini以显著更少的参数量取得了与KANICE相当的性能：在SVHN数据集上，KANICE-mini以2,337,828个参数达到90.00%的准确率，而KANICE需要25,432,000个参数。本研究凸显了基于KAN的架构在图像分类任务中平衡性能与计算效率的潜力。我们的工作推动了自适应神经网络的研究，将数学定理融入深度学习架构，并探索了模型复杂度与性能之间的权衡，从而促进了计算机视觉与模式识别领域的发展。本文源代码已通过GitHub仓库（https://github.com/m-ferdaus/kanice）公开提供。