Electrically programmable phase-change photonic memory for optical neural networks with nanoseconds in situ training capability

Wei, Min; Li, Junying; Chen, Zequn; Tang, Bo; Jia, Zhi Xin; Zhang, Peng; Lei, Kunhao; Xu, Kai; Wu, Jianghong; Zhong, Chuyu; Ma, Hui; Ye, Yuting; Jian, Jialing; Sun, Chunlei; Liu, Ruonan; Sun, Yu; Sha, Wei E. I.; Hu, Xiaoyong; Yang, Jianyi; Li, Lan; Lin, Hongtao

doi:10.1117/1.ap.5.4.046004

Cited by 29 publications

(7 citation statements)

References 60 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Note that this is the first report that more than 222 levels are achieved in PCM-integrated photonic devices. This value is nearly seven times higher than that realized in the state-of-the-art device (∼32 levels), ,, detailed comparison shown in Supporting Information of Table S5. Precisely tuning multilevel contributes to improve the learning ability and recognition accuracy of neural networks …”

Section: Resultsmentioning

confidence: 67%

Seven Bit Nonvolatile Electrically Programmable Photonics Based on Phase-Change Materials for Image Recognition

Xia,

Wang,

Wang

et al. 2024

ACS Photonics

View full text Add to dashboard Cite

With the rapid development of the Internet of Things, how to efficiently store, transmit, and process massive amounts of data has become a major challenge now. Optical neural networks based on nonvolatile phase change materials (PCMs) have become a breakthrough point due to their zero static power consumption, low thermal crosstalk, large-scale, and high efficiency. However, current photonic devices cannot meet the multilevel requirements in neuromorphic computing due to their limited storage capacity. Here, a new way for increasing storage capacity is paved from the perspective of modulation of the crystallization kinetics of PCMs. A more progressive transition from the amorphous to the crystalline states is achieved through the grain-refinement phenomenon induced by nitrogen (N) element doping in Ge 2 Sb 2 Te 5 (GST), giving precise access to more multibit states. By integrating N-doped Ge 2 Sb 2 Te 5 (N-GST) with a waveguide, a high-capacity nonvolatile photonic device enabling over 7 bits (∼222 levels) storage is achieved for the first time. The storage capacity is increased nearly by 7 times compared to the state-of-the-art device (∼32 levels). An optical convolutional neural network is successfully established for the MINIST handwritten digit recognition task by mapping synapse weight to the multiple optical levels, and a recognition accuracy of up to 96.5% is achieved. Our work provides a new strategy for the development of integrated photonic devices with multilevel and demonstrates enormous application potential in the field of large-scale photonic neural networks.

show abstract

Section: Resultsmentioning

confidence: 67%

Seven Bit Nonvolatile Electrically Programmable Photonics Based on Phase-Change Materials for Image Recognition

Xia,

Wang,

Wang

et al. 2024

ACS Photonics

View full text Add to dashboard Cite

show abstract

“…While there has been significant research development on low-loss PCMs in the amorphous and crystalline states, the study of the multilevel intermediate states at the micron scale is still in its infancy [37]. The research on programmable PCM-based PICs and metasurfaces primarily utilized thermal annealing and electrothermal switching [38][39][40][41]. As a result, programmable PICs and metasurfaces with ultra-high flexibility in phase modulation using multi-level PCMs with free-space laser switching were rarely reported, to the best of our knowledge.…”

Section: Introductionmentioning

confidence: 99%

Pixelated non-volatile programmable photonic integrated circuits with 20-level intermediate states

Chen,

Liu,

Zhu

2024

Int. J. Extrem. Manuf.

View full text Add to dashboard Cite

Multi-level programmable photonic integrated circuits and optical metasurfaces have gained widespread attention in many fields, such as neuromorphic photonics, optical communications, and quantum information. In this paper, we propose pixelated programmable Si3N4 photonic integrated circuits with record-high 20-level intermediate states at 785 nm wavelength. Such flexibility in phase or amplitude modulation is achieved by a programmable Sb2S3 matrix, the footprint of whose elements can be as small as 1.2 μm, limited only by the optical diffraction limit of an in-house developed pulsed laser writing system. We believe, our work lays the foundation for laser-writing ultra-high-level (20 levels and even more) programmable photonic systems and metasurfaces based on phase change materials, which could catalyze diverse applications such as programmable neuromorphic photonics, biosensing, optical computing, photonic quantum computing, and reconfigurable metasurfaces.

show abstract

“…Chalcogenide phase change materials, such as an example, can be directly deposited on silicon and have attracted signi cant attention thanks to their nonvolatile properties [17][18][19][20] , making them promising candidates for compact (~ 10 µm) and zero-static power photonic devices. In the past decades, a plethora of PCM-integrated recon gurable photonic devices have been extensively developed for intensity modulation [21][22][23][24][25][26][27][28][29] , phase tuning [30][31][32][33] , and light path switching 34,35 . Moreover, they play a crucial role in constructing photonic networks and serve as essential elements for optical storage 36 , inmemory computing 37 , and analog optical computing 38,39 .…”

Section: Introductionmentioning

confidence: 99%

“Zero change” platform for monolithic back-end-of-line integration of phase change materials in silicon photonics

Lin,

Wei,

et al. 2023

Preprint

Self Cite

View full text Add to dashboard Cite

Monolithic integration of novel materials for unprecedented device functions without modifying the existing photonic component library is the key to advancing heterogeneous silicon photonic integrated circuits. To achieve this, the introduction of a silicon nitride etching stop layer at selective area, coupled with low-loss oxide trench to waveguide surface, enables the incorporation of various functional materials without disrupting the reliability of foundry-verified devices. As an illustration, two distinct chalcogenide phase change materials (PCM) with remarkable nonvolatile modulation capabilities, namely Sb2Se3 and Ge2Sb2Se4Te1, were monolithic back-end-of-line integrated into silicon photonics. The PCM enables compact phase and intensity tuning units with zero-static power consumption. Taking advantage of these building blocks, the phase error of a push-pull Mach-Zehnder interferometer optical switch could be trimmed by a nonvolatile phase shifter with a 48% peak power consumption reduction. Mirco-ring filters with a rejection ratio >25dB could be applied for >5-bit wavelength selective intensity modulation, and waveguide-based >7-bit intensity-modulation photonic attenuators could achieve >39dB broadband attenuation. The advanced “Zero change” back-end-of-line integration platform could not only facilitate the integration of PCMs for integrated reconfigurable photonics but also open up the possibilities for integrating other excellent optoelectronic materials in the future silicon photonic process design kits.

show abstract

Electrically programmable phase-change photonic memory for optical neural networks with nanoseconds in situ training capability

Cited by 29 publications

References 60 publications

Seven Bit Nonvolatile Electrically Programmable Photonics Based on Phase-Change Materials for Image Recognition

Seven Bit Nonvolatile Electrically Programmable Photonics Based on Phase-Change Materials for Image Recognition

Pixelated non-volatile programmable photonic integrated circuits with 20-level intermediate states

“Zero change” platform for monolithic back-end-of-line integration of phase change materials in silicon photonics

Contact Info

Product

Resources

About