Coherent Optical
Coherent optical technology manipulates the amplitude and phase of light for high-speed data transmission and advanced imaging, primarily focusing on improving the efficiency and reliability of optical communication systems. Current research emphasizes developing and optimizing neural network-based equalizers, employing architectures like convolutional neural networks (CNNs), long short-term memory (LSTMs), and transformers, to compensate for channel impairments and enhance signal quality. These advancements are crucial for increasing data rates in fiber optic networks and enabling new applications such as full-wavefield lidar, which offers improved ranging accuracy and velocimetry capabilities.
Papers
Reducing Computational Complexity of Neural Networks in Optical Channel Equalization: From Concepts to Implementation
Pedro J. Freire, Antonio Napoli, Diego Arguello Ron, Bernhard Spinnler, Michael Anderson, Wolfgang Schairer, Thomas Bex, Nelson Costa, Sergei K. Turitsyn, Jaroslaw E. Prilepsky
Exploiting Deep Reinforcement Learning for Edge Caching in Cell-Free Massive MIMO Systems
Yu Zhang, Shuaifei Chen, Jiayi Zhang