Fully analog end-to-end online training with real-time adaptibility on integrated photonic platform

TL;DR

This paper presents a silicon photonic integrated circuit capable of real-time, end-to-end analog training for neuromorphic processing, demonstrating high accuracy and robustness in dynamic environments with on-chip adaptive learning.

Contribution

It introduces a fully integrated photonic platform with in-situ gradient descent for real-time adaptive learning, advancing scalable analog neuromorphic systems.

Findings

Achieved over 90% accuracy in classification tasks.

Demonstrated real-time adaptive tracking of changing inputs.

Maintained robustness against temperature fluctuations.

Abstract

Analog neuromorphic photonic processors are uniquely positioned to harness the ultrafast bandwidth and inherent parallelism of light, enabling scalability, on-chip integration and significant improvement in computational performance. However, major challenges remain unresolved especially in achieving real-time online training, efficient end-to-end anolog systems, and adaptive learning for dynamical environmental changes. Here, we demonstrate an on-chip photonic analog end-to-end adaptive learning system realized on a foundry-manufactured silicon photonic integrated circuit. Our platform leverages a multiplexed gradient descent algorithm to perform in-situ, on-the-fly training, while maintaining robustness in online tracking and real-time adaptation. At its core, the processor features a monolithic integration of a microring resonator weight bank array and on-chip photodetectors, enabling direct optical measurement of gradient signals. This eliminates the need for high-precision digital matrix multiplications, significantly reducing computational overhead and latency, an essential requirement for effective online training. We experimentally demonstrate real-time, end-to-end analog training for both linear and nonlinear classification tasks at gigabaud rates, achieving accuracies of over 90\% and 80\%, respectively. Our analog neuromorphic processor introduces self-learning capabilities that dynamically adjust training parameters, setting the stage for truly autonomous neuromorphic architectures capable of efficient, real-time processing in unpredictable real-world environments. As a result, we showcase adaptive online tracking of dynamically changing input datasets and achieve over 90\% accuracy, alongside robustness to external temperature fluctuations and internal thermal crosstalk.