English(EN)QuantKAN: A Unified Quantization Framework for Kolmogorov Arnold Networks
新的KAN框架和变体提高了研究和效率
作者PulseAugur 编辑部·[12 个来源]·
研究人员开发了KANLib，一个旨在通过整合现有实现（如PyKAN、EfficientKAN和FastKAN）的特性来简化Kolmogorov-Arnold网络（KANs）研究的新框架。同时，引入了一个名为MKAN的新变体，它通过B样条系数的指数重新参数化，理论上保证了KANs的单调性。此外，PH-KAN为使用KANs进行非线性系统识别提供了一种保留结构的方法，提高了可解释性。最后，QuantKAN为KANs的量化提供了一个统一的框架，探索了量化感知训练和训练后量化方法，以提高低精度硬件上的效率。
AI
arXiv:2606.20326v1 Announce Type: new Abstract: We develop QCPIKAN, the first quantum-classical physics-informed Kolmogorov-Arnold network designed to solve partial differential equations (PDEs). Built upon Chebyshev-polynomial KAN layers and parameterized quantum circuits, this …
arXiv:2606.19984v1 Announce Type: new Abstract: Reservoir computing offers a lightweight framework for forecasting dynamical systems but may struggle to capture long-range dependencies due to limited representational capacity. Conventional reservoir computing recurrently uses tra…
We develop QCPIKAN, the first quantum-classical physics-informed Kolmogorov-Arnold network designed to solve partial differential equations (PDEs). Built upon Chebyshev-polynomial KAN layers and parameterized quantum circuits, this hybrid framework embeds physical constraints int…
Reservoir computing offers a lightweight framework for forecasting dynamical systems but may struggle to capture long-range dependencies due to limited representational capacity. Conventional reservoir computing recurrently uses trainable reservoirs with hyperparameter sensitivit…
arXiv cs.LG
TIER_1English(EN)·Duc Hoang, Aarush Gupta, Philip Harris·
arXiv:2512.12850v3 Announce Type: replace-cross Abstract: Low-latency, resource-efficient neural network inference on FPGAs is essential for applications demanding real-time capability and low power. Lookup table (LUT)-based neural networks are a common solution, combining strong…
arXiv:2606.17886v1 Announce Type: new Abstract: Monotonicity has been a long-running architectural inductive bias for neural networks, motivated by tabular, scientific, and economic settings where outputs are known to respond monotonically to certain inputs. Existing approaches a…
arXiv cs.AI
TIER_1English(EN)·Julian Hoever, Gregor Schiele·
arXiv:2606.17927v1 Announce Type: cross Abstract: Kolmogorov-Arnold Networks (KANs) have recently emerged as a promising alternative to traditional multilayer perceptrons by replacing linear weights with learnable univariate functions. Despite their theoretical advantages in inte…
Kolmogorov-Arnold Networks (KANs) have recently emerged as a promising alternative to traditional multilayer perceptrons by replacing linear weights with learnable univariate functions. Despite their theoretical advantages in interpretability and expressiveness, practical researc…
Monotonicity has been a long-running architectural inductive bias for neural networks, motivated by tabular, scientific, and economic settings where outputs are known to respond monotonically to certain inputs. Existing approaches are MLP- or flow-based and lack per-edge function…
arXiv:2606.14708v1 Announce Type: cross Abstract: Data-driven machine learning approaches have become increasingly attractive for nonlinear system identification, but standard models often fail to preserve the underlying physical structure and remain difficult to interpret, espec…
arXiv cs.LG
TIER_1English(EN)·James Li, Philip H. W. Leong, Thomas Chaffey·
arXiv:2603.10562v2 Announce Type: replace-cross Abstract: Monotone operator equilibrium networks are implicit-layer models whose output is the unique equilibrium of a monotone operator, guaranteeing existence, uniqueness, and convergence. When deployed on low-precision hardware, …
arXiv cs.LG
TIER_1English(EN)·Kazi Ahmed Asif Fuad, Lizhong Chen·
arXiv:2511.18689v3 Announce Type: replace Abstract: Kolmogorov--Arnold Networks (KANs) replace linear weights with spline-based functions, offering strong expressivity but posing challenges for low-precision deployment due to heterogeneous parameter distributions. We introduce Qu…
