• A Hybrid Conference – In-Person and Virtual Presentations
  • Technical Conference:  05 – 09 March 2023
  • Exhibition: 07 – 09 March 2023
  • San Diego Convention Center, San Diego, California, USA

Roadmap for Photonic AI Accelerators


Volker Sorger, George Washington University, USA
Nikos Pleros, Aristotle University of Thessaloniki, Greece
Xian Xiao, Hewlett Packard Labs, USA
Glenn Bartolini, Coherent Corp​, USA


In addition to the known high-bandwidth benefit, photonics offers two key functionalities with relevance to AI accelerators for machine learning, namely, multiplication and accumulation such as enabled via, for example, modulators and photodetectors, respectively. However, photonics is challenged to provide end-to-end neural network solutions reflected by the challenge of a nonlinear activation function leading to OEO conversions. This channels realisations of deep neural network architectures in the optical domain requiring electronics introducing parasitic conversions. In addition optical accelerators being analog compute engines may require (depending on the application) digital-to-analog domain crossing which is expensive. 

In this panel we will review the state-of-the-art in photonic AI accelerators and will project challenges and solutions into the future for photonic and hybrid accelerators for AI and machine intelligence. Here our perspective is open to application spaces in network edge AI and to machine learning training in the cloud.


Darius Bunandar, Lightmatter, USA

Hamed Dalir, UCLA, USA

Johannes Feldman, Salence Labs, UnitedKingdom

Bahram Jalali, UCLA, USA

Francesca Parmigianni, Microsoft Research Cambridge, UnitedKingdom