SEPhIA: <1 laser/neuron Spiking Electro-Photonic Integrated Multi-Tiled Architecture for Scalable Optical Neuromorphic Computing

2025-10-08

AI Summary

Existing photonic spiking neural network (SNN) studies often neglect critical physical constraints—including optical power limitations, inter-channel crosstalk, and chip area overhead. To address this, we propose SEPhIA: a scalable, optoelectronic, multi-die neuromorphic architecture. SEPhIA integrates microring resonator modulators (MRMs), CMOS–photonics co-designed coupling circuits, and multi-wavelength laser sources to achieve ultra-low-power operation—fewer than one laser per neuron. It supports physics-aware, end-to-end training and employs time-domain co-simulation calibrated with measured device parameters. Evaluated on four spike-coded classification tasks, SEPhIA achieves >90% accuracy—matching near-software-level performance. Crucially, its design-space analysis is the first to quantitatively characterize how key device parameters govern SNN accuracy under noise-limited conditions.

Technology Category

• Cognitive Modeling & Cognitive Systems: Neural Spike Coding
• Machine Learning: Hardware-aware ML
• Search and Optimization: Learning to Search

Application Category

• Search and Retrieval-Augmented AI: Efficiency and scalability of Web search engines
• Systems and Infrastructure for Web, Mobile and WoT: Applied ML and AI for Web-based mobile applications
• Responsible Web: Machine-in-the-loop, human agency and autonomy

Abstract

Research into optical spiking neural networks (SNNs) has primarily focused on spiking devices, networks of excitable lasers or numerical modelling of large architectures, often overlooking key constraints such as limited optical power, crosstalk and footprint. We introduce SEPhIA, a photonic-electronic, multi-tiled SNN architecture emphasizing implementation feasibility and realistic scaling. SEPhIA leverages microring resonator modulators (MRMs) and multi-wavelength sources to achieve effective sub-one-laser-per-spiking neuron efficiency. We validate SEPhIA at both device and architecture levels by time-domain co-simulating excitable CMOS-MRR coupled circuits and by devising a physics-aware, trainable optoelectronic SNN model, with both approaches utilizing experimentally derived device parameters. The multi-layer optoelectronic SNN achieves classification accuracies over 90% on a four-class spike-encoded dataset, closely comparable to software models. A design space study further quantifies how photonic device parameters impact SNN performance under constrained signal-to-noise conditions. SEPhIA offers a scalable, expressive, physically grounded solution for neuromorphic photonic computing, capable of addressing spike-encoded tasks.

Problem

• Addresses optical power limitations and crosstalk in scalable optical SNNs
• Develops photonic-electronic architecture with sub-one-laser-per-neuron efficiency
• Validates physically realistic SNN performance under signal-to-noise constraints

Innovation

• Uses microring resonator modulators and multi-wavelength sources
• Achieves sub-one-laser-per-spiking neuron efficiency
• Validates through time-domain co-simulation and physics-aware modeling