Monolithically integrated photonic neural network at driven-dissipative criticality
Abstract
Artificial intelligence increasingly demands computing architectures capable of adaptive representation, temporal information processing, and robust operation under uncertainty. However, conventional photonic neural architectures typically rely on predefined computational operations and separate functional modules, limiting the ability of physical systems to exploit their intrinsic dynamics for intelligence. Here, we demonstrate a monolithically integrated active photonic neural network (APNN) that harnesses driven-dissipative criticality as a physical computational resource. By balancing optical excitation and dissipation, the system operates near a critical regime where weak input-dependent variations are amplified into separable representations while stable attractor dynamics are preserved. The APNN integrates an optoelectronic nonlinear array and a reconfigurable symmetric optical coupling matrix on a silicon photonic chip, enabling recurrent physical computation within a compact closed loop. We demonstrate nonlinear classification with 95.2% accuracy using only 100 training samples and 44 trainable parameters. And it remains robust at an ultralow signal-to-noise ratio of -30 dB. Beyond static recognition, the same driven-dissipative dynamics enable long-range temporal feature extraction from electrocardiogram signals and associative recovery of corrupted patterns through attractor-based relaxation. These results establish driven-dissipative criticality as a unified mechanism for representation enhancement, temporal information retention, and error-resilient computation, providing a pathway toward scalable photonic systems in which intelligence emerges from intrinsic physical dynamics.
Related
- Electro-optic comb-driven massive data transmission on monolithically integrated lithium niobate photonic circuits
- Low-divergence GaSb-based semiconductor lasers via monolithically integrated MMI transverse-field engineering
- From Effective Temperature to Non-Boltzmann State Selection in Driven-Dissipative Quantum Criticality
- Nonlinear Dissipation and Hopf Criticality in Driven Dissipative Collective Spins
- Interferometric Readout of Momentum-Space Topology in a Programmable Dissipative Photonic Circuit
BibTeX
@misc{zhang2026monolithically,
title = {{Monolithically integrated photonic neural network at driven-dissipative criticality}},
author = {Yuming Zhang and Ruoran Wang and Jingcheng Li and Hailong Zhou and Jianji Dong and Zhipei Sun and Xinliang Zhang},
howpublished = {arXiv},
year = {2026},
month = sep,
doi = {10.48550/arxiv.2609.34171},
eprint = {2609.34171},
archivePrefix = {arXiv},
url = {https://arxiv.org/abs/2609.34171},
}
RIS
TY - UNPB
TI - Monolithically integrated photonic neural network at driven-dissipative criticality
AU - Yuming Zhang
AU - Ruoran Wang
AU - Jingcheng Li
AU - Hailong Zhou
AU - Jianji Dong
AU - Zhipei Sun
AU - Xinliang Zhang
PY - 2026
DA - 2026/09/28
PB - arXiv
DO - 10.48550/arxiv.2609.34171
UR - https://arxiv.org/abs/2609.34171
AB - Artificial intelligence increasingly demands computing architectures capable of adaptive representation, temporal information processing, and robust operation under uncertainty. However, conventional photonic neural architectures typically rely on predefined computational operations and separate functional modules, limiting the ability of physical systems to exploit their intrinsic dynamics for intelligence. Here, we demonstrate a monolithically integrated active photonic neural network (APNN) that harnesses driven-dissipative criticality as a physical computational resource. By balancing optical excitation and dissipation, the system operates near a critical regime where weak input-dependent variations are amplified into separable representations while stable attractor dynamics are preserved. The APNN integrates an optoelectronic nonlinear array and a reconfigurable symmetric optical coupling matrix on a silicon photonic chip, enabling recurrent physical computation within a compact closed loop. We demonstrate nonlinear classification with 95.2% accuracy using only 100 training samples and 44 trainable parameters. And it remains robust at an ultralow signal-to-noise ratio of -30 dB. Beyond static recognition, the same driven-dissipative dynamics enable long-range temporal feature extraction from electrocardiogram signals and associative recovery of corrupted patterns through attractor-based relaxation. These results establish driven-dissipative criticality as a unified mechanism for representation enhancement, temporal information retention, and error-resilient computation, providing a pathway toward scalable photonic systems in which intelligence emerges from intrinsic physical dynamics.
ER -