Highly efficient convolution computing architecture based on silicon photonic Fano resonance devices

Jiarong Ni, Wenda Lu, Xiaohan Lai, Lidan Lu, Jianzhen Ou, Lianqing Zhu

Optoelectronics Letters ›› 2023, Vol. 19 ›› Issue (11) : 646-652.

Optoelectronics Letters ›› 2023, Vol. 19 ›› Issue (11) : 646-652. DOI: 10.1007/s11801-023-3047-4
Article

Highly efficient convolution computing architecture based on silicon photonic Fano resonance devices

Author information +
History +

Abstract

Convolutional neural networks (CNNs) require a lot of multiplication and addition operations completed by traditional electrical multipliers, leading to high power consumption and limited speed. Here, a silicon waveguide-based wavelength division multiplexing (WDM) architecture for CNN is optimized with high energy efficiency Fano resonator. Coupling of T-waveguide and micro-ring resonator generates Fano resonance with small half-width, which can significantly reduce the modulator power consumption. Insulator dataset from state grid is used to test Fano resonance modulator-based CNNs. The results show that accuracy for insulator defect recognition reaches 99.27% with much lower power consumption. Obviously, our optimized photonic integration architecture for CNNs has broad potential for the artificial intelligence hardware platform.

Cite this article

Download citation ▾
Jiarong Ni, Wenda Lu, Xiaohan Lai, Lidan Lu, Jianzhen Ou, Lianqing Zhu. Highly efficient convolution computing architecture based on silicon photonic Fano resonance devices. Optoelectronics Letters, 2023, 19(11): 646‒652 https://doi.org/10.1007/s11801-023-3047-4

References

[1]
PérezD, GasullaI, CrudgingtonL, et al.. Multipurpose silicon photonics signal processor core[J]. Nature communications, 2017, 8(1):636
CrossRef Google scholar
[2]
LiuW, LiM, GuzzonR S, et al.. A fully reconfigurable photonic integrated signal processor[J]. Nature photonics, 2016, 10(3): 190-195
CrossRef Google scholar
[3]
HarrisN C, BunandarD, PantM, et al.. Large-scale quantum photonic circuits in silicon[J]. Nanophotonics, 2016, 5(3):456-468
CrossRef Google scholar
[4]
TaitA N, De LimaT F, ZhouE, et al.. Neuromorphic photonic networks using silicon photonic weight banks[J]. Scientific reports, 2017, 7(1):1-10
CrossRef Google scholar
[5]
ShenY, HarrisN C, SkirloS, et al.. Deep learning with coherent nanophotonic circuits[J]. Nature photonics, 2017, 11(7):441-446
CrossRef Google scholar
[6]
ShainlineJ M, BuckleyS M, MirinR P, et al.. Superconducting optoelectronic circuits for neuromor-phic computing[J]. Physical review applied, 2017, 7(3):034013
CrossRef Google scholar
[7]
ZhangH, GuM, JiangX D, et al.. An optical neural chip for implementing complex-valued neural network[J]. Nature communications, 2021, 12(1): 457
CrossRef Google scholar
[8]
XuS, WangJ, YiS, et al.. High-order tensor flow processing using integrated photonic circuits[J]. Nature communications, 2022, 13(1): 7970
CrossRef Google scholar
[9]
MiscuglioM, SorgerV J. Photonic tensor cores for machine learning[J]. Applied physics reviews, 2020, 7(3): 031404
CrossRef Google scholar
[10]
MehrabianA, Al-KabaniY, SorgerV J, et al.. A photonic convolutional neural network accelerator[C], 2018, New York, IEEE: 169-173
[11]
ZhouH, QiuC, JiangX, et al.. Compact, submilliwatt, 2×2 silicon thermo-optic switch based on photonic crystal nanobeam cavities[J]. Photonics research, 2017, 5(2):108-112
CrossRef Google scholar
[12]
LuL, ZhuL, ZengZ, et al.. Fano resonance ion sensor enabled by 2D plasmonic sub-nanopores-material[J]. IEEE sensors journal, 2021, 21(13):14776-14783
CrossRef Google scholar
[13]
XuY, LuL, ChenG, et al.. T-shaped silicon waveguide coupled with a micro-ring resonator-based Fano resonance modulator[J]. Applied optics, 2022, 61(31):9217-9224
CrossRef Google scholar
[14]
TaoX, ZhangD, WangZ, et al.. Detection of power line insulator defects using aerial images analyzed with convolutional neural networks[J]. IEEE transactions on systems, man, and cybernetics: systems, 2018, 50(4):1486-1498
CrossRef Google scholar
[15]
GuL, FangL, FangH, et al.. Fano resonance lineshapes in a waveguide-microring structure enabled by an air-hole[J]. APL photonics, 2020, 5(1):016108
CrossRef Google scholar
[16]
ZhangY, ZouJ, HeJ J. Temperature sensor with enhanced sensitivity based on silicon Mach-Zehnder interferometer with waveguide group index engineering[J]. Optics express, 2018, 26(20): 26057-26064
CrossRef Google scholar
[17]
DingZ, LiuP, ChenJ, et al.. On-chip simultaneous sensing of humidity and temperature with a dual-polarization silicon microring resonator[J]. Optics express, 2019, 27(20):28649-28659
CrossRef Google scholar
[18]
ChenF, ZhangH, SunL, et al.. Temperature tunable Fano resonance based on ring resonator side coupled with a MIM waveguide[J]. Optics & laser technology, 2019, 116: 293-299
CrossRef Google scholar
[19]
XuY, OuZ, ChenJ, et al.. High sensitivity refractive index and temperature sensors with tunable multiple fano resonances[C], 2021, New York, IEEE: 239-242
[20]
ZhengH, MaR, ZhuZ. A linear and wide dynamic range transimpedance amplifier with adaptive gain control technique[J]. Analog integrated circuits and signal processing, 2017, 90: 217-226
CrossRef Google scholar
[21]
RahimA, SpuesensT, BaetsR, et al.. Open-access silicon photonics: current status and emerging initiatives[J]. Proceedings of the IEEE, 2018, 106(12):2313-2330
CrossRef Google scholar
[22]
NedeljkovicM, SorefR, MashanovichG Z. Free-carrier electrorefraction and electroabsorption modulation predictions for silicon over the 1–14 µm infrared wavelength range[J]. IEEE photonics journal, 2011, 3(6):1171-1180
CrossRef Google scholar
[23]
Van MieghemP, MertensR P, Van OverstraetenR J. Theory of the junction capacitance of an abrupt diode[J]. Journal of applied physics, 1990, 67(9):4203-4211
CrossRef Google scholar

Accesses

Citations

Detail

Sections
Recommended

/