QuKAN:一种面向量子 Kolmogorov Arnold Networks 的量子电路 Born 机方法
QuKAN: A Quantum Circuit Born Machine approach to Quantum Kolmogorov Arnold Networks
AI总结:
本研究利用量子电路 Born 机(QCBM)在混合与全量子形式下实现了 KAN 架构,通过预训练残差函数发挥参数化量子电路的表示能力,验证了 QuKAN 架构的可行性、可解释性与性能。
摘要:
基于 Kolmogorov Arnold 表示定理(KAR)构建的 Kolmogorov Arnold Networks(KANs),在以更少神经元表达复杂函数方面展现出了有前景的能力。与多层感知机(MLPs)等传统网络不同,这是通过在边而非节点上实现可学习参数来实现的。然而,KANs 在量子机器学习中的潜力尚未得到充分探索。在本研究中,我们使用量子电路 Born 机(QCBM)以混合和全量子两种形式实现了这些 KAN 架构。我们利用预训练残差函数调整 KAN 迁移,从而利用参数化量子电路的表示能力。在混合模型中,我们将经典 KAN 组件与量子子程序相结合;而在全量子版本中,残差函数的整个架构被转化为量子模型。我们论证了所提出的 Quantum KAN(QuKAN)架构的可行性、可解释性与性能。
英文摘要:
Kolmogorov Arnold Networks (KANs), built upon the Kolmogorov Arnold representation theorem (KAR), have demonstrated promising capabilities in expressing complex functions with fewer neurons. This is achieved by implementing learnable parameters on the edges instead of on the nodes, unlike traditional networks such as Multi-Layer Perceptrons (MLPs). However, KANs potential in quantum machine learning has not yet been well explored. In this work, we present an implementation of these KAN architectures in both hybrid and fully quantum forms using a Quantum Circuit Born Machine (QCBM). We adapt the KAN transfer using pre-trained residual functions, thereby exploiting the representational power of parametrized quantum circuits. In the hybrid model we combine classical KAN components with quantum subroutines, while the fully quantum version the entire architecture of the residual function is translated to a quantum model. We demonstrate the feasibility, interpretability and performance of the proposed Quantum KAN (QuKAN) architecture.
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。