Quality Analysis of a Photonic Micro-ring Resonator

Uddin, M. Rakib; Siang, Teo Kui; Munarah, Nor; Norfauzi, Muhammad; Ahmed, Nazri; Salam, Md. Abdus

doi:10.1109/iccce.2016.87

Cited by 9 publications

(2 citation statements)

References 7 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…FSR is a parameter that describes spaces between resonant frequencies. In MRR, it is calculated in following formula [14]:…”

Section: B Coupling Coefficientmentioning

confidence: 99%

Photonic micro-ring resonator design and analysis using machine learning techniques

Nurgali,

Molardi,

Nakarmi

et al. 2024

Silicon Photonics XIX

View full text Add to dashboard Cite

Micro-ring resonators (MRRs) have emerged as vital components in photonic applications, offering precise control of light at the nanoscale. Achieving optimal MRR design parameters is crucial for maximizing their performance in high-speed applications. This study aims to employ feature engineering and supervised machine learning (ML) techniques to comprehensively analyze MRRs. This includes impact of change in MRR design geometries, such as radius, coupling geometry, waveguide properties to key MRR output parameters, including the quality factor, full width at half maximum (FWHM), rise/fall time, and free spectral range (FSR). By utilizing results of over 1000 simulations in Lumerical, as well as incorporating the theoretical knowledge of MRRs, the study seeks to build highly accurate predictive model.

show abstract

“…FSR is a parameter that describes spaces between resonant frequencies. In MRR, it is calculated in following formula [14]:…”

Section: B Coupling Coefficientmentioning

confidence: 99%

Photonic micro-ring resonator design and analysis using machine learning techniques

Nurgali,

Molardi,

Nakarmi

et al. 2024

Silicon Photonics XIX

View full text Add to dashboard Cite

show abstract

“…Therefore, we select an optimal MRM of diameter of 10µm to minimize overall insertion loss. Furthermore, we have considered an FSR of 20nm based on the device-level analysis presented in prior work [34] on an MRM of diameter 10µm. In line with this MRM FSR, each waveguide is expected to have 16 DWDM with a channel spacing of 1.25nm (see Table 2).…”

Section: Sensitivity Analysis With Prediction Accuracymentioning

confidence: 99%

BPLight-CNN: A Photonics-Based Backpropagation Accelerator for Deep Learning

Dang

Chittamuru

Pasricha

et al. 2021

J. Emerg. Technol. Comput. Syst.

View full text Add to dashboard Cite

Training deep learning networks involves continuous weight updates across the various layers of the deep network while using a backpropagation (BP) algorithm. This results in expensive computation overheads during training. Consequently, most deep learning accelerators today employ pretrained weights and focus only on improving the design of the inference phase. The recent trend is to build a complete deep learning accelerator by incorporating the training module. Such efforts require an ultra-fast chip architecture for executing the BP algorithm. In this article, we propose a novel photonics-based backpropagation accelerator for high-performance deep learning training. We present the design for a convolutional neural network (CNN), BPLight-CNN , which incorporates the silicon photonics-based backpropagation accelerator. BPLight-CNN is a first-of-its-kind photonic and memristor-based CNN architecture for end-to-end training and prediction. We evaluate BPLight-CNN using a photonic CAD framework (IPKISS) on deep learning benchmark models, including LeNet and VGG-Net. The proposed design achieves (i) at least 34× speedup, 34× improvement in computational efficiency, and 38.5× energy savings during training; and (ii) 29× speedup, 31× improvement in computational efficiency, and 38.7× improvement in energy savings during inference compared with the state-of-the-art designs. All of these comparisons are done at a 16-bit resolution, and BPLight-CNN achieves these improvements at a cost of approximately 6% lower accuracy compared with the state-of-the-art.

show abstract