Compute with Light: Architectures, Technologies and Training Models for Neuromorphic Photonic Circuits
Nikos Pleros, Miltiadis Moralis‐Pegios, Angelina Totović, George Dabos, Apostolos Tsakyridis, George Giamougiannis, George Mourgias-Alexandris, Nikos Passalis, Manos Kirtas, Anastasios Tefas
Abstract
We discuss recent advances in the field of neuromorphic photonics, presenting our recent work and perspective towards optimizing the architecture, the enabling technology and the Deep Learning training models through a hardware/software co-design and co-development framework.
Topics & Concepts
Neuromorphic engineeringComputer architectureComputer sciencePhotonicsPerspective (graphical)Field (mathematics)Deep learningSoftwareArchitectureArtificial intelligenceComputer engineeringArtificial neural networkMaterials scienceProgramming languageMathematicsPure mathematicsOptoelectronicsVisual artsArtNeural Networks and Reservoir ComputingAdvanced Memory and Neural ComputingOptical Network Technologies