Design automation of photonic resonator weights

Autor: Ferreira de Lima Thomas, Doris Eli A., Bilodeau Simon, Zhang Weipeng, Jha Aashu, Peng Hsuan-Tung, Blow Eric C., Huang Chaoran, Tait Alexander N., Shastri Bhavin J., Prucnal Paul R.

Publikováno v: Nanophotonics, Vol 11, Iss 17, Pp 3805-3822 (2022)

Neuromorphic photonic processors based on resonator weight banks are an emerging candidate technology for enabling modern artificial intelligence (AI) in high speed analog systems. These purpose-built analog devices implement vector multiplications w

Externí odkaz: https://doaj.org/article/cbf3bf7a16c84203922a924d8b39c276

A manufacturable platform for photonic quantum computing

Autor: Alexander, Koen, Bahgat, Andrea, Benyamini, Avishai, Black, Dylan, Bonneau, Damien, Burgos, Stanley, Burridge, Ben, Campbell, Geoff, Catalano, Gabriel, Ceballos, Alex, Chang, Chia-Ming, Chung, CJ, Danesh, Fariba, Dauer, Tom, Davis, Michael, Dudley, Eric, Er-Xuan, Ping, Fargas, Josep, Farsi, Alessandro, Fenrich, Colleen, Frazer, Jonathan, Fukami, Masaya, Ganesan, Yogeeswaran, Gibson, Gary, Gimeno-Segovia, Mercedes, Goeldi, Sebastian, Goley, Patrick, Haislmaier, Ryan, Halimi, Sami, Hansen, Paul, Hardy, Sam, Horng, Jason, House, Matthew, Hu, Hong, Jadidi, Mehdi, Johansson, Henrik, Jones, Thomas, Kamineni, Vimal, Kelez, Nicholas, Koustuban, Ravi, Kovall, George, Krogen, Peter, Kumar, Nikhil, Liang, Yong, LiCausi, Nicholas, Llewellyn, Dan, Lokovic, Kimberly, Lovelady, Michael, Manfrinato, Vitor, Melnichuk, Ann, Souza, Mario, Mendoza, Gabriel, Moores, Brad, Mukherjee, Shaunak, Munns, Joseph, Musalem, Francois-Xavier, Najafi, Faraz, O'Brien, Jeremy L., Ortmann, J. Elliott, Pai, Sunil, Park, Bryan, Peng, Hsuan-Tung, Penthorn, Nicholas, Peterson, Brennan, Poush, Matt, Pryde, Geoff J., Ramprasad, Tarun, Ray, Gareth, Rodriguez, Angelita, Roxworthy, Brian, Rudolph, Terry, Saunders, Dylan J., Shadbolt, Pete, Shah, Deesha, Shin, Hyungki, Smith, Jake, Sohn, Ben, Sohn, Young-Ik, Son, Gyeongho, Sparrow, Chris, Staffaroni, Matteo, Stavrakas, Camille, Sukumaran, Vijay, Tamborini, Davide, Thompson, Mark G., Tran, Khanh, Triplet, Mark, Tung, Maryann, Vert, Alexey, Vidrighin, Mihai D., Vorobeichik, Ilya, Weigel, Peter, Wingert, Mathhew, Wooding, Jamie, Zhou, Xinran

Whilst holding great promise for low noise, ease of operation and networking, useful photonic quantum computing has been precluded by the need for beyond-state-of-the-art components, manufactured by the millions. Here we introduce a manufacturable pl

Externí odkaz: http://arxiv.org/abs/2404.17570

Nanophotonic cavity based synapse for scalable photonic neural networks

Autor: Jha, Aashu, Huang, Chaoran, deLima, Thomas Ferriera, Peng, Hsuan-Tung, Shastri, Bhavin, Prucnal, Paul R.

The bandwidth and energy demands of neural networks has spurred tremendous interest in developing novel neuromorphic hardware, including photonic integrated circuits. Although an optical waveguide can accommodate hundreds of channels with THz bandwid

Externí odkaz: http://arxiv.org/abs/2203.01128

Photonic spiking neural networks and CMOS-compatible graphene-on-silicon spiking neurons

Autor: Jha, Aashu, Huang, Chaoran, Peng, Hsuan-Tung, Shastri, Bhavin, Prucnal, Paul R.

Spiking neural networks are known to be superior over artificial neural networks for their computational power efficiency and noise robustness. The benefits of spiking coupled with the high-bandwidth and low-latency of photonics can enable highly-eff

Externí odkaz: http://arxiv.org/abs/2109.13797

Silicon microring synapses enable photonic deep learning beyond 9-bit precision

Autor: Zhang, Weipeng, Huang, Chaoran, Peng, Hsuan-Tung, Bilodeau, Simon, Jha, Aashu, Blow, Eric, De Lima, Thomas Ferreira, Shastri, Bhavin J., Prucnal, Paul

Deep neural networks (DNN) consist of layers of neurons interconnected by synaptic weights. A high bit-precision in weights is generally required to guarantee high accuracy in many applications. Minimizing error accumulation between layers is also es

Externí odkaz: http://arxiv.org/abs/2104.01164