Reinforcement learning for photonic component design

Article Nanoscience & Nanotechnology

Deep reinforcement learning empowers automated inverse design and optimization of photonic crystals for nanoscale laser cavities

Renjie Li et al.

Summary: Photonics inverse design is traditionally done by human experts, which is labor-intensive, slow, and sub-optimal. This study proposes L2DO, a reinforcement learning-based method that autonomously designs nanophotonic laser cavities and outperforms human experts by over 2 orders of magnitude. L2DO can bypass the shortage of training data, non-unique solutions, and optimization limitations of traditional supervised or semi-supervised learning approaches.

NANOPHOTONICS (2023)

添加到收藏夹

Article Nanoscience & Nanotechnology

Detection of Single W-Centers in Silicon

Yoann Baron et al.

Summary: This study demonstrates the detection of single intrinsic defects in silicon and reveals new information about their radiation damage center properties. The microscopic structure and radiative recombination mechanism of these defects below the silicon bandgap are identified. These results are of great significance for conducting quantum research based on intrinsic luminescent defects in silicon.

ACS PHOTONICS (2022)

添加到收藏夹

Article Optics

Silicon photonic quantum computing with spin qubits

Xiruo Yan et al.

Summary: Universal quantum computing has the potential to revolutionize the information-based society, but a hardware platform for fault-tolerant quantum computing remains elusive. One proposed platform involves using circuit-bound photons and solid-state spin qubits for measurement-based quantum computations, but practical implementation faces challenges. Silicon is identified as a leading candidate for hosting such a platform.

APL PHOTONICS (2021)

添加到收藏夹

Article Materials Science, Multidisciplinary

Deep Reinforcement Learning for Digital Materials Design

Fanping Sui et al.

Summary: This paper introduces the concept of digital materials and their application in composite material design. Through a deep reinforcement learning scheme, an automated process for digital material design is achieved, resulting in improved design quality and significant computational advantages.

ACS MATERIALS LETTERS (2021)

添加到收藏夹

Proceedings Paper Engineering, Electrical & Electronic

SiEPICfab: the Canadian silicon photonics rapid-prototyping foundry for integrated optics and quantum computing

Adam Darcie et al.

Summary: SiEPICfab aims to research the fabrication of silicon photonic devices and integrated circuits, making cutting-edge silicon photonics manufacturing accessible globally. It offers rapid prototyping facilities to support the entire ecosystem of companies involved in silicon photonics product development.

SILICON PHOTONICS XVI (2021)

添加到收藏夹

Article Multidisciplinary Sciences