Tag
This paper introduces KANalogue, a fully analogue implementation of Kolmogorov-Arnold Networks that uses negative-differential-resistance devices to perform learnable nonlinear functions directly in hardware. It achieves competitive accuracy with fewer parameters than analogue MLPs on MNIST, FashionMNIST, and CIFAR-10.
This paper proposes quantum-inspired recurrent models (QKAN-FWPs) for traffic-matrix forecasting, demonstrating superior accuracy with fewer parameters compared to LSTM baselines.
We propose hierarchical RBF-KAN and RBF-SKAN architectures for multidimensional function approximation and random field learning. The frameworks offer universal approximation properties and partially alleviate the curse of dimensionality, with empirical results showing improved accuracy over existing methods.
This paper introduces Gated QKAN-FWP, a scalable quantum-inspired sequence learning framework that combines Fast Weight Programmers with Kolmogorov-Arnold Networks using single-qubit data re-uploading circuits.