Publications by authors named "Yigong Yang"

We propose and numerically demonstrate a photonic time-delay reservoir computing (TDRC) system exhibiting enhanced parallel task processing performance, where an optically injected vertical-cavity surface-emitting laser (VCSEL) under random distributed optical feedback acts as the reservoir computer. To assess its effectiveness, we perform two benchmark tasks including chaotic time-series prediction and waveform recognition task, where the TDRC is associated with two different random feedback structures, i.e.

View Article and Find Full Text PDF
Article Synopsis
  • Time-delay reservoir computing (TDRC) is a simplified form of recurrent neural networks that uses a feedback mechanism to create virtual nodes, and its performance can be improved by using deeper architectures.
  • The researchers introduce a new approach called photonic deep residual TDRC (DR-TDRC), which incorporates time delays into the residual structure, resulting in enhanced memory capabilities and significantly better performance in tasks like nonlinear channel equalization compared to traditional deep networks.
  • They validate their concept with a 4-layer DR-TDRC system made up of 960 interconnected neurons and demonstrate its potential for scalable deep photonic computing, addressing the growing needs for artificial intelligence advancements.
View Article and Find Full Text PDF
Article Synopsis
  • The study introduces a photonic time-delay reservoir computing (TDRC) system that utilizes random distributed optical feedback to improve performance under optical injection.
  • The performance evaluation includes measuring memory ability and conducting tasks like chaotic time series prediction and nonlinear channel equalization, revealing superior results compared to single optical feedback systems.
  • The experimental findings indicate that the random feedback enhances nonlinearity in the reservoir laser, marking a significant advancement in TDRC technology.
View Article and Find Full Text PDF

We propose and numerically demonstrate a high-speed photonic reservoir computing (RC) system using a compact Fano laser (FL) with optical feedback under electrical modulation. Benefiting from its insensitivity to external feedback, an FL has a wider dynamic steady-state region compared with a conventional Fabry-Perot laser, which significantly extends the ranges of desirable RC implementation. Interestingly, we observe two separate regions of good RC performances corresponding to two scenarios of the dynamic steady state of the FL, respectively.

View Article and Find Full Text PDF

Time-delay signature (TDS) suppression of an external-cavity semiconductor laser (ECSL) is important for chaos-based applications and has been widely studied in the literature. In this paper, the chaotic output of an ECSL is injected into a semiconductor laser and TDS suppression in the regenerated time series is revisited. The focus of the current work is the influence of parameter mismatch on the TDS evolution, which is investigated experimentally and compared systematically to simulations.

View Article and Find Full Text PDF