Photonic KAN：一种受Kolmogorov-Arnold网络启发的高效光子神经形态架构
Photonic KAN: a Kolmogorov-Arnold network inspired efficient photonic neuromorphic architecture
AI总结：
受KAN启发提出Photonic KAN全光神经形态平台，用级联环形辅助MZI实现边侧光学非线性，相比现有光子网络参数缩放和可解释性更优，同性能下能耗面积降65倍、延迟降50倍。
摘要：
Kolmogorov-Arnold网络（KAN）模型是近期被提出的一类模型，据称与传统多层感知器（MLP）模型相比，具备更优的参数缩放特性与可解释性。受KAN架构启发，我们提出了Photonic KAN——一种集成式全光神经形态平台，该平台利用沿KAN边分布的高参数化光学非线性传递函数实现计算。在本研究中，我们以级联环形辅助马赫-曾德尔干涉仪（MZI）器件的形式实现了这类非线性特性。这一创新设计有望解决当前光子神经网络的核心局限性。在我们的测试用例中，与现有光子神经网络相比，Photonic KAN展现出更优的参数缩放性能与可解释性。针对函数拟合任务，在性能相近的前提下，Photonic KAN的能耗与芯片面积较此前基于MZI的光子加速器降低约65倍，延迟降低50倍。这一突破为拓展神经形态硬件平台的可扩展性与效率提供了极具前景的新方向。
英文摘要：
Kolmogorov-Arnold Networks (KAN) models were recently proposed and claimed to provide improved parameter scaling and interpretability compared to conventional multilayer perceptron (MLP) models. Inspired by the KAN architecture, we propose the Photonic KAN -- an integrated all-optical neuromorphic platform leveraging highly parametric optical nonlinear transfer functions along KAN edges. In this work, we implement such nonlinearities in the form of cascaded ring-assisted Mach-Zehnder Interferometer (MZI) devices. This innovative design has the potential to address key limitations of current photonic neural networks. In our test cases, the Photonic KAN showcases enhanced parameter scaling and interpretability compared to existing photonic neural networks. The photonic KAN achieves approximately 65$\times$ reduction in energy consumption and area, alongside a 50$\times$ reduction in latency compared to previous MZI-based photonic accelerators with similar performance for function fitting task. This breakthrough presents a promising new avenue for expanding the scalability and efficiency of neuromorphic hardware platforms.
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。
