A programmable topological photonic chip

Nature Materials, Journal Year: 2024, Volume and Issue: 23(7), P. 928 - 936

Published: May 22, 2024

Controlling topological phases of light allows the observation abundant phenomena and development robust photonic devices. The prospect more sophisticated control with devices for practical implementations requires high-level programmability. Here we demonstrate a fully programmable chip large-scale integration silicon nanocircuits microresonators. Photonic artificial atoms their interactions in our compound system can be individually addressed controlled, allowing arbitrary adjustment structural parameters geometrical configurations dynamic phase transitions diverse insulators. Individual programming on generic enables comprehensive statistical characterization robustness against relatively weak disorders, counterintuitive Anderson induced by strong disorders. This rapidly reprogrammed to implement multifunctionalities, providing flexible versatile platform applications across fundamental science technologies.

Language: Английский

---

Freeform direct-write and rewritable photonic integrated circuits in phase-change thin films

Science Advances, Journal Year: 2024, Volume and Issue: 10(1)

Published: Jan. 5, 2024

Photonic integrated circuits (PICs) with rapid prototyping and reprogramming capabilities promise revolutionary impacts on a plethora of photonic technologies. We report direct-write rewritable low-loss phase-change material (PCM) thin film. Complete end-to-end PICs are directly laser-written in one step without additional fabrication processes, any part the circuit can be erased rewritten, facilitating design modification. demonstrate versatility this technique for diverse applications, including an optical interconnect fabric reconfigurable networking, crossbar array computing, tunable filter signal processing. By combining programmability direct laser writing PCM, our unlocks opportunities programmable Moreover, enable testing convenient cost-efficient manner, eliminate need nanofabrication facilities, thus promote proliferation photonics research education to broader community.

Language: Английский

---

Optical neural networks: progress and challenges

Light Science & Applications, Journal Year: 2024, Volume and Issue: 13(1)

Published: Sept. 20, 2024

Language: Английский

---

Partial coherence enhances parallelized photonic computing

Nature, Journal Year: 2024, Volume and Issue: 632(8023), P. 55 - 62

Published: July 31, 2024

Abstract Advancements in optical coherence control 1–5 have unlocked many cutting-edge applications, including long-haul communication, light detection and ranging (LiDAR) tomography 6–8 . Prevailing wisdom suggests that using more coherent sources leads to enhanced system performance device functionalities 9–11 Our study introduces a photonic convolutional processing takes advantage of partially boost computing parallelism without substantially sacrificing accuracy, potentially enabling larger-size tensor cores. The reduction the degree optimizes bandwidth use system. This breakthrough challenges traditional belief is essential or even advantageous integrated accelerators, thereby with less rigorous feedback thermal-management requirements for high-throughput computing. Here we demonstrate such two platforms applications: core phase-change-material memories delivers parallel convolution operations classify gaits ten patients Parkinson’s disease 92.2% accuracy (92.7% theoretically) silicon embedded electro-absorption modulators (EAMs) facilitate 0.108 tera per second (TOPS) classifying Modified National Institute Standards Technology (MNIST) handwritten digits dataset 92.4% (95.0% theoretically).

Language: Английский

---

Characterizing soil Cops Eco-risk in China

Journal of Hazardous Materials, Journal Year: 2025, Volume and Issue: 489, P. 137588 - 137588

Published: Feb. 11, 2025

Language: Английский

---

An integrated large-scale photonic accelerator with ultralow latency

Nature, Journal Year: 2025, Volume and Issue: 640(8058), P. 361 - 367

Published: April 9, 2025

Integrated photonics, particularly silicon have emerged as cutting-edge technology driven by promising applications such short-reach communications, autonomous driving, biosensing and photonic computing1-4. As advances in AI lead to growing computing demands, has gained considerable attention an appealing candidate. Nonetheless, there are substantial technical challenges the scaling up of integrated photonics systems realize these advantages, ensuring consistent performance gains upscaled device clusters, establishing standard designs verification processes for complex circuits, well packaging large-scale systems. These obstacles arise primarily because relative immaturity manufacturing scarcity advanced solutions involving photonics. Here we report a accelerator comprising more than 16,000 components. The is designed deliver linear matrix multiply-accumulate (MAC) functions, enabling with high speed 1 GHz frequency low latency small 3 ns per cycle. Logic, memory control functions that support MAC operations were into cointegrated electronics chip. To seamlessly integrate chips at commercial scale, made use innovative 2.5D hybrid approach. Through development this system, demonstrate ultralow computation heuristic solvers computationally hard Ising problems whose greatly relies on latency.

Language: Английский

---

Electrically programmable phase-change photonic memory for optical neural networks with nanoseconds in situ training capability

Advanced Photonics, Journal Year: 2023, Volume and Issue: 5(04)

Published: July 18, 2023

Optical neural networks (ONNs), enabling low latency and high parallel data processing without electromagnetic interference, have become a viable player for fast energy-efficient calculation to meet the increasing demand hash rate. Photonic memories employing nonvolatile phase-change materials could achieve zero static power consumption, thermal cross talk, large-scale, high-energy-efficient photonic networks. Nevertheless, switching speed dynamic energy consumption of material-based make them inapplicable in situ training. Here, by integrating patch phase change thin film with PIN-diode-embedded microring resonator, bifunctional memory both 5-bit storage nanoseconds volatile modulation was demonstrated. For first time, concept is presented electrically programmable material-driven integrated nanosecond allow training ONNs. ONNs an optical convolution kernel constructed our theoretically achieved accuracy predictions higher than 95% when tested MNIST handwritten digit database. This provides feasible solution constructing large-scale high-speed capability.

Language: Английский

---

Determining the optimal communication channels of arbitrary optical systems using integrated photonic processors

Nature Photonics, Journal Year: 2023, Volume and Issue: 18(2), P. 149 - 155

Published: Nov. 23, 2023

Language: Английский

---

Backpropagation-free training of deep physical neural networks

Science, Journal Year: 2023, Volume and Issue: 382(6676), P. 1297 - 1303

Published: Nov. 23, 2023

Recent successes in deep learning for vision and natural language processing are attributed to larger models but come with energy consumption scalability issues. Current training of digital deep-learning primarily relies on backpropagation that is unsuitable physical implementation. In this work, we propose a simple neural network architecture augmented by local (PhyLL) algorithm, which enables supervised unsupervised networks without detailed knowledge the nonlinear layer's properties. We trained diverse wave-based vowel image classification experiments, showcasing universality our approach. Our method shows advantages over other hardware-aware schemes improving speed, enhancing robustness, reducing power eliminating need system modeling thus decreasing computation.

Language: Английский

---

Artificial neural networks for photonic applications—from algorithms to implementation: tutorial

Advances in Optics and Photonics, Journal Year: 2023, Volume and Issue: 15(3), P. 739 - 739

Published: Aug. 3, 2023

This tutorial-review on applications of artificial neural networks in photonics targets a broad audience, ranging from optical research and engineering communities to computer science applied mathematics. We focus here the areas at interface between these disciplines, attempting find right balance technical details specific each domain overall clarity. First, we briefly recall key properties peculiarities some core network types, which believe are most relevant photonics, also linking layer's theoretical design hardware realizations. After that, elucidate question how fine-tune selected model's perform required task with optimized accuracy. Then, review part, discuss recent developments progress for several including multiple aspects communications, imaging, sensing, new materials lasers. In following section, put special emphasis accurately evaluate complexity context transition algorithms implementation. The introduced characteristics used analyze as specific, albeit highly important example, comparing those benchmark signal processing methods. combine description well-known model compression strategies machine learning, novel techniques recently networks. It is stress that although our this methods presented can be handy much wider range scientific applications.

Language: Английский

---