All-Optical Nonlinear Activation Function Based on Germanium Silicon Hybrid Asymmetric Coupler

Li, Hengkang; Wu, Bo; Tong, Weiyu; Dong, Jianji; Zhang, Chi

doi:10.1109/jstqe.2022.3166510

Cited by 13 publications

(7 citation statements)

References 34 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…They claim that these devices are suitable for low-power ONNs. In 2022, Dong’s group proposed an all-optical realization of a nonlinear activation function based on the hybrid integration of germanium (Ge) and silicon by using the plasmonic dispersion effect and carrier absorption effect of Ge at 1550 nm (Figure b) . This scheme has a large operating bandwidth with the response frequency of 70 MHz, a low loss of 4.28 dB, and a low threshold power of 5.1 mW.…”

Section: Implementations Of On-chip Optical Nonlinear Activationsmentioning

confidence: 99%

“…In 2022, Dong's group proposed an all-optical realization of a nonlinear activation function based on the hybrid integration of germanium (Ge) and silicon by using the plasmonic dispersion effect and carrier absorption effect of Ge at 1550 nm (Figure 4b). 96 This scheme has a large operating bandwidth with the response frequency of 70 MHz, a low loss of 4.28 dB, and a low threshold power of 5.1 mW. In 2022, Hu's group proposed and experimentally verified the performance of a single-layer graphene with optical nonlinear saturable absorption effect covered on a silicon waveguide as a nonlinear activation layer in an on-chip integrated locally connected photonic neural network (Figure 4c).…”

Section: ■ Implementations Of On-chip Optical Nonlinear Activationsmentioning

confidence: 99%

See 1 more Smart Citation

Integrated Photonic Neural Networks: Opportunities and Challenges

et al. 2023

View full text Add to dashboard Cite

Photonic neural networks benefit from the use of photons to perform intelligent inference computing with ultrafast and ultralow energy consumption in ultra-high-throughput, providing the efficient photonic hardware for the new generation of intelligent computing, and the effective way to support large-scale integration for on-chip all-optical computing chips. With the rapid development of photonic neural networks, demands for efficient computation power have increased dramatically. However, the weak and impractical optical nonlinear activations, the lack of suitable configurations for integrated photonic hardware, and proper optical storage mediums pose challenges to this field. In this Perspective, we propose our current point of view and a suggestive roadmap in the field of integrated photonic platform for optical neural networks. Throughout the discussion, we highlight recent progresses meeting with major challenges. We also identify some next challenges still ahead to realize integrated photonic neural networks capable of matching the current computational power of graphic cards.

show abstract

Section: Implementations Of On-chip Optical Nonlinear Activationsmentioning

confidence: 99%

Section: ■ Implementations Of On-chip Optical Nonlinear Activationsmentioning

confidence: 99%

Integrated Photonic Neural Networks: Opportunities and Challenges

et al. 2023

View full text Add to dashboard Cite

show abstract

“…and weight (w) during the training process 22 . To train the ONN, we implemented the backpropagation algorithm with the RMSProp optimizer and a batch size of 750 over the course of 500 epochs.…”

Section: Static Characteristic Of the Silicon-graphene All-optical Ac...mentioning

confidence: 99%

“…For example, the silicon microring resonator (MRR) has been combined with various materials, such as phase change materials (PCMs) 20,21 , and the nonlinear effects of these materials have been utilized to achieve OAFs. Although the use of an MRR enhances the nonlinearity of the device, there are still the shortcomings of slow response speed and narrow optical bandwidth, which limit processing capability of ONNs 22 . Indeed, the existing approaches for constructing OAFs all exhibit inherent de ciencies that signi cantly hinder the advancement of ONNs.…”

Section: Introductionmentioning

confidence: 99%

Ultrafast Silicon Optical Nonlinear Activator for Neuromorphic Computing

Yan

Zhou

Liu

et al. 2023

Preprint

View full text Add to dashboard Cite

Optical neural networks (ONNs) have shown great promise in overcoming the speed and efficiency bottlenecks of artificial neural networks (ANNs). However, the absence of high-speed, energy-efficient nonlinear activators significantly impedes the advancement of ONNs and their extension to ultrafast application scenarios like autonomous vehicles and real-time intelligent signal processing. In this work, we designed and fabricated a novel silicon-based ultrafast all-optical nonlinear activator, leveraging the hybrid integration of silicon slot waveguides, plasmonic slot waveguides, and monolayer graphene. We utilized double-balanced detection and synchronous pump-probe measurement techniques to experimentally evaluate the static and dynamic characteristics of the activators, respectively. Exploiting the exceptional picosecond scale photogenerated carrier relaxation time of graphene, the response time of the activator is markedly reduced to ~93.6 ps. This response time is approximately five times faster than electronic neural networks, establishing our all-optical activator as the fastest known in silicon photonics to our knowledge. Moreover, the all-optical nonlinear activator holds a low threshold power of 5.49 mW and a corresponding power consumption per activation of 0.51 pJ. Furthermore, we confirm its feasibility and capability for use in ONNs by simulation, achieving a high accuracy of 96.8% for MNIST handwritten digit recognition and a mean absolute error of less than 0.1 dB for optical signal-to-noise ratio monitoring of high-speed optical signals. This breakthrough in speed and energy efficiency of all-optical nonlinear activators opens the door to significant improvements in the performance and applicability of ONNs, ushering in a new era of advanced artificial intelligence technologies with enormous potential.

show abstract

“…Semiconductor optical amplifiers offer high gain saturation and short carrier lifetimes but face challenges regarding cost and power consumption 3,4 . Meanwhile , silicon microring resonators combined with special materials, such as phase change materials, show potential but suffer from slow response speeds and narrow optical bandwidth 5 . Therefore, the realization of a high-speed, energy-efficient nonlinear component has always been the goal pursued by researchers.…”

Section: Introductionmentioning

confidence: 99%

Ultrafast all-optical nonlinear activator employing silicon/graphene hybrid integration

Yan

2024

Machine Learning in Photonics

View full text Add to dashboard Cite

Graphene is a two-dimensional material with a hexagonal lattice structure made up of carbon atoms, which has exceptional optoelectronic properties such as high thermal conductivity, broad light absorption wavelength, and ultrafast carrier mobility. As a result, various graphene-based optoelectronic devices have been developed with exceptional performance. In this talk, an ultrafast all-optical nonlinear activator with a response time of 93.6 ps will be presented. This breakthrough in speed of all-optical nonlinear activators opens the door to significant improvements in the performance and applicability of ONNs.

show abstract

All-Optical Nonlinear Activation Function Based on Germanium Silicon Hybrid Asymmetric Coupler

Cited by 13 publications

References 34 publications

Integrated Photonic Neural Networks: Opportunities and Challenges

Integrated Photonic Neural Networks: Opportunities and Challenges

Ultrafast Silicon Optical Nonlinear Activator for Neuromorphic Computing

Ultrafast all-optical nonlinear activator employing silicon/graphene hybrid integration

Contact Info

Product

Resources

About