Sigang Yang

Dr. Sigang Yang

Beijing National Research Center for Information Science and Technology (BNRist), Department of Electronic Engineering, Tsinghua University, Beijing 100084, China

Research Focus & Metrics

Academic Career Length

15Years (2012-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
5 January 2023 in Nature Communications
Verified
Journal Article
Open access
PDF file
TFTingzhao Fu
Tingzhao Fu
YZYubin Zang
Yubin Zang
YHYuyao Huang
Yuyao Huang
ZDZhenmin Du
Zhenmin Du
HHHonghao Huang
Honghao Huang
HCHongwei Chen
Hongwei Chen
Machine learning technologies have been extensively applied in high-performance information-processing fields. However, the computation rate of existing hardware is severely circumscribed by conventional Von Neumann architecture. Photonic approaches have demonstrated extraordinary potential for executing deep learning processes that involve complex calculations. In this work, an on-chip diffractive optical neural network (DONN) based on a silicon-on-insulator platform is proposed to perform machine learning tasks with high integration and low power consumption characteristics. To validate the proposed DONN, we fabricated 1-hidden-layer and 3-hidden-layer on-chip DONNs with footprints of 0.15 mm2 and 0.3 mm2 and experimentally verified their performance on the classification task of the Iris plants dataset, yielding accuracies of 86.7% and 90%, respectively. Furthermore, a 3-hidden-layer on-chip DONN is fabricated to classify the Modified National Institute of Standards and Technology handwritten digit images. The proposed passive on-chip DONN provides a potential solution for accelerating future artificial intelligence hardware with enhanced performance.

4 May 2022 in Light: Science & Applications
Verified
Journal Article
Open access
PDF file
WSWanxin Shi
Wanxin Shi
ZHZheng Huang
Zheng Huang
HHHonghao Huang
Honghao Huang
CHChengyang Hu
Chengyang Hu
MCMinghua Chen
Minghua Chen
HCHongwei Chen
Hongwei Chen
Machine vision faces bottlenecks in computing power consumption and large amounts of data. Although opto-electronic hybrid neural networks can provide assistance, they usually have complex structures and are highly dependent on a coherent light source; therefore, they are not suitable for natural lighting environment applications. In this paper, we propose a novel lensless opto-electronic neural network architecture for machine vision applications. The architecture optimizes a passive optical mask by means of a task-oriented neural network design, performs the optical convolution calculation operation using the lensless architecture, and reduces the device size and amount of calculation required. We demonstrate the performance of handwritten digit classification tasks with a multiple-kernel mask in which accuracies of as much as 97.21% were achieved. Furthermore, we optimize a large-kernel mask to perform optical encryption for privacy-protecting face recognition, thereby obtaining the same recognition accuracy performance as no-encryption methods. Compared with the random MLS pattern, the recognition accuracy is improved by more than 6%.

26 July 2024 in Science Advances
Verified
Journal Article
Open access
ZHZheng Huang
Zheng Huang
WSWanxin Shi
Wanxin Shi
SWShukai Wu
Shukai Wu
YWYaode Wang
Yaode Wang
Sigang YangSigang Yang
Sigang Yang
HCHongwei Chen
Hongwei Chen
Moving computation units closer to sensors is becoming a promising approach to addressing bottlenecks in computing speed, power consumption, and data storage. Pre-sensor computing with optical neural networks (ONNs) allows extensive processing. However, the lack of nonlinear activation and dependence on laser input limits the computational capacity, practicality, and scalability. A compact and passive multilayer ONN (MONN) is proposed, which has two convolution layers and an inserted nonlinear layer, performing pre-sensor computations with designed passive masks and a quantum dot film for incoherent light. MONN has an optical length as short as 5 millimeters, two orders of magnitude smaller than state-of-the-art lens-based ONNs. MONN outperforms linear single-layer ONN across various vision tasks, off-loading up to 95% of computationally expensive operations into optics from electronics. Motivated by MONN, a paradigm is emerging for mobile vision, fulfilling the demands for practicality, miniaturization, and low power consumption.

31 December 2021 in Journal of Lightwave Technology
Verified
Journal Article
Closed access
YZYubin Zang
Yubin Zang
ZYZHEN MING YU
ZHEN MING YU
KXKun Xu
Kun Xu
XLXingzeng Lan
Xingzeng Lan
MCMinghua Chen
Minghua Chen
HCHongwei Chen
Hongwei Chen
In this paper, a novel principle-driven fiber transmission model based on physical induced neural network (PINN) is proposed. Unlike data-driven models which regard fiber transmission problem as data regression tasks, this model views it as an equation solving problem. Instead of adopting input signals and output signals which are calculated by SSFM algorithm in advance before training, this principle-driven PINN based fiber model adopts frames of time and distance as its inputs and the corresponding real and imaginary parts of NLSE solutions as its outputs. By taking into account of pulses and signals before transmission as initial conditions and fiber physical principles as NLSE in the design of loss functions, this model will progressively learn the transmission rules. Therefore, it can be effectively trained without the data labels, referred as the pre-calculated signals after transmission in data-driven models. Due to this advantage, SSFM algorithm is no longer needed before the training of principle-driven fiber model which can save considerable time consumption. Through numerical demonstration, the results show that this principle-driven PINN based fiber model can handle the prediction tasks of pulse evolution, signal transmission and fiber birefringence for different transmission parameters of fiber telecommunications.

24 March 2025 in Light: Science & Applications
Verified
Journal Article
Open access
PDF file
WLWencan Liu
Wencan Liu
YHYuyao Huang
Yuyao Huang
RSRun Sun
Run Sun
TFTingzhao Fu
Tingzhao Fu
Sigang YangSigang Yang
Sigang Yang
HCHongwei Chen
Hongwei Chen
To enhance the computational density and energy efficiency of on-chip neuromorphic hardware, this study introduces a novel network architecture for multi-task processing with in-memory optical computing. On-chip optical neural networks are celebrated for their capability to transduce a substantial volume of parameters into optical form while conducting passive computing, yet they encounter challenges in scalability and multitasking. Leveraging the principles of transfer learning, this approach involves embedding the majority of parameters into fixed optical components and a minority into adjustable electrical components. Furthermore, with deep regression algorithm in modeling physical propagation process, a compact optical neural network achieve to handle diverse tasks. In this work, two ultra-compact in-memory diffraction-based chips with integration of more than 60,000 parameters/mm2 were fabricated, employing deep neural network model and the hard parameter sharing algorithm, to perform multifaceted classification and regression tasks, respectively. The experimental results demonstrate that these chips achieve accuracies comparable to those of electrical networks while significantly reducing the power-intensive digital computation by 90%. Our work heralds strong potential for advancing in-memory optical computing frameworks and next generation of artificial intelligence platforms.

1 December 2025 in Light: Science & Applications
Verified
Journal Article
Open access
JHJunling Hu
Junling Hu
SZSa Zhang
Sa Zhang
MCMeiyu Cai
Meiyu Cai
MMMingjian Ma
Mingjian Ma
SLShuguang Li
Shuguang Li
Sigang YangSigang Yang
Sigang Yang
Optical fiber interferometric sensors are of great importance in chemistry, biology, and medicine disciplines owing to high-sensitivity and high-quality factor. However, due to the limitation of free spectral range, the inherent trade-off between wide measurement range and high sensitivity poses a persistent challenge in interference sensor development, which has fundamentally hindered their widespread adoption in precision measurement applications. In this work, a long short-term memory neural network is utilized in a Mach-Zehnder interference-based refractive index sensor to break the free spectral range limitation. Unique gating mechanism in long short-term memory neural network enables it to efficiently process long-term dependent sequence information, such as interference spectrum, avoiding the need for complex spectral signal analysis. A one-to-one mapping relationship is established between the interference spectrum and refractive index with root mean square error of 3.029 × 10 −4 and a coefficient of determination of 0.99971. The measurement range is extended from a single free spectral range of 1.3333–1.3561 to approximately three free spectral ranges of 1.3333–1.3921 without sacrificing sensitivity. Moreover, a wider measurement range can be achieved with sufficient training data. This work successfully resolves the inherent contradiction between high sensitivity and wide dynamic measurement range in optical interference-based sensors, opening up a path for the next generation of intelligent sensing systems.