Photonic KAN: a Kolmogorov-Arnold network inspired efficient photonic neuromorphic architecture

TL;DR

The paper introduces Photonic KAN, an all-optical neuromorphic architecture inspired by Kolmogorov-Arnold Networks, achieving significant improvements in energy efficiency, area, and latency over previous photonic neural networks.

Contribution

It presents a novel integrated all-optical neuromorphic platform utilizing cascaded ring-assisted MZI devices for nonlinear transfer functions, enhancing scalability and interpretability.

Findings

65x reduction in energy and area

50x reduction in latency

Enhanced parameter scaling and interpretability

Abstract

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.