
Advanced Optical Materials, Journal Year: 2025, Volume and Issue: unknown
Published: March 20, 2025
Abstract Neuromorphic photonics has become one of the research forefronts in photonics, with its benefits low‐latency signal processing and potential significant energy consumption reduction when compared digital electronics. With artificial intelligence (AI) computing accelerators high demand, high‐impact goals is to build scalable neuromorphic photonic integrated circuits which can accelerate AI models at efficiency. A complete system comprises seven stacks: materials, devices, circuits, microarchitecture, architecture, algorithms, applications. Here, we consider microring resonator (MRR)‐based network designs toward building silicon neural networks (PNN), variations MRR resonance wavelength from fabrication process their impact on PNN scalability. Further, post‐fabrication using organic photochromic layers over platform shown be effective for trimming variation, significantly reduce MRR‐based configuration. Post‐fabrication materials compensate variation will allow a chip without sacrificing today's performance metrics, critical commercial viability volume production large‐scale circuits.
Language: Английский