Dalir’s CHIP Lab Integrates ML with Optical Networks

Dr. Hamed Dalir’s CHIP Lab at the University of Florida published a new paper in Nature Communications Physics (DOI:10.1038/s42005-024-01571-3), showcasing their groundbreaking research on integrating machine learning within optical networks. The team’s novel hybrid optical-electronic convolutional neural network (CNN) system, which incorporates Fourier optics convolution to demultiplex multiplexed orbital angular momentum (OAM) beams, marks a significant advancement in optical computing and communication technologies.

“Our work has unveiled new insights into the demultiplexing of OAM beams, which will be leveraged for the development of integrated optical-electronic convolutional neural networks.”
—Jiachi Ye, doctoral candidate

The system was designed by Jiachi Ye, a doctoral candidate at the CHIP lab in the Department of Electrical and Computer Engineering (ECE) at the University of Florida.

ECE Assistant Research Professors Dr. Hao Wang and Dr. Chandraman Patil added, “To overcome the performance limitations imposed by conventional spatial light modulators and cameras within our OAM-based optical CNN systems, the team is exploring the implementation of advanced metasurfaces and developing custom-designed, high-speed spatial light modulators, aiming to significantly enhance the modulation efficiency, speed, and resolution of the optical components used in their systems.”

The potential use of OAM beams in augmenting data transmission throughput and boosting system efficiency was underscored by Dr. Dalir, the principal investigator of the CHIP Lab. The results illustrate the capability of the hybrid optical-electronic CNN accelerator to reduce the overall system latency and energy consumption in optical computing and communications. According to Dr. Dalir and Ye, an integrated optical-electronic communication system running at a system frequency of 350 GHz has been proposed. The present work has the potential to impact the domain of optical computing and communication significantly. Fourier optics will provide extensive parallel convolution, hence broadening the scope of applications for optical manipulation using OAM, microscopic particles in optical tweezers, encrypted communication, and introducing new prospects in these domains.