Online training and pruning of multi-wavelength photonic neural networks

Abstract

CMOS-compatible photonic integrated circuits (PICs) are emerging as a promising platform in artificial intelligence (AI) computing. Owing to the compact footprint of microring resonators (MRRs) and the enhanced interconnect efficiency enabled by wavelength division multiplexing (WDM), MRR-based photonic neural networks (PNNs) are particularly promising for large-scale integration. However, the scalability and energy efficiency of such systems are fundamentally limited by the MRR resonance wavelength variations induced by fabrication process variations (FPVs) and environmental fluctuations. Existing solutions use post-fabrication approaches or thermo-optic tuning, incurring high control power and additional process complexity. In this work, we introduce an online training and pruning method that addresses this challenge, adapting to FPV-induced and thermally induced shifts in MRR resonance wavelength. By incorporating a power-aware pruning term into the conventional loss function, our approach simultaneously optimizes the PNN accuracy and the total power consumption for MRR tuning. In proof-of-concept on-chip experiments on the Iris dataset, our system PNNs can adaptively train to maintain a 96% classification accuracy, while achieving a 44.7% reduction in tuning power via pruning. Additionally, our approach reduces the power consumption by orders-of-magnitude on larger datasets. By addressing chip-to-chip variation and minimizing power requirements, our approach significantly improves the scalability and energy efficiency of MRR-based integrated analog photonic processors, paving the way for large-scale PICs to enable versatile applications including neural networks, photonic switching, LiDAR, and radio-frequency beamforming.

arXiv comment21 pages, 5 figures

References in corpus (18)

• Deep Learning with Coherent Nanophotonic Circuits
• All-Optical Machine Learning Using Diffractive Deep Neural Networks
• Parallel convolution processing using an integrated photonic tensor core
• Photonics for artificial intelligence and neuromorphic computing
• Neuromorphic Silicon Photonic Networks
• Single-chip photonic deep neural network for instantaneous image classification
• Large-scale neuromorphic optoelectronic computing with a reconfigurable diffractive processing unit
• Training of photonic neural networks through in situ backpropagation
• A one femtojoule athermal silicon modulator
• Experimentally realized in situ backpropagation for deep learning in nanophotonic neural networks
• Single chip photonic deep neural network with accelerated training
• Wavelength tuning and stabilization of microring-based filters using silicon in-resonator photoconductive heaters
• Silicon Photonic Architecture for Training Deep Neural Networks with Direct Feedback Alignment
• Photoconductive Heaters Enable Control of Large-Scale Silicon Photonic Ring Resonator Circuits
• Trainable and Dynamic Computing: Error Backpropagation through Physical Media
• Quantifying power use in silicon photonic neural networks
• Beam Steering with Ultracompact and Low-Power Silicon Resonator Phase Shifters
• Multiplexed gradient descent: Fast online training of modern datasets on hardware neural networks without backpropagation