2019 · 45 citations · 15 references
EngineeringComputer EngineeringComputer ScienceComputer ArchitectureMachine LearningPhotonicsDeep LearningNeural NetworksNeural Signal ProcessingOptical Signal ProcessingSilicon PhotonicsArea-efficient DesignMach-zehnder InterferometersNeuromorphic HardwareOptical ComputingOptical InterferometersOptical Neural NetworksPower-efficient ArchitectureSingular Value Decomposition
Optical neural network (ONN) is a neuromorphic computing hardware based on optical components. Since its first on-chip experimental demonstration, it has attracted more and more research interests due to the advantages of ultra-high speed inference with low power consumption. In this work, we design a novel slimmed architecture for realizing optical neural network considering both its software and hardware implementations. Different from the originally proposed ONN architecture based on singular value decomposition which results in two implementation-expensive unitary matrices, we show a more area-efficient architecture which uses a sparse tree network block, a single unitary block and a diagonal block for each neural network layer. In the experiments, we demonstrate that by leveraging the training engine, we are able to find a comparable accuracy to that of the previous architecture, which brings about the flexibility of using the slimmed implementation. The area cost in terms of the Mach-Zehnder interferometers, the core optical components of ONN, is 15%-38% less for various sizes of optical neural networks.
15
Deep learning with coherent nanophotonic circuits
Yichen Shen, Nicholas C. Harris, Scott A. Skirlo et al. · Nature Photonics · 2017 · 3.1K citations · Full text
Experimental realization of any discrete unitary operator
Michael Reck, Anton Zeilinger, H. J. Bernstein et al. · Physical Review Letters · 1994 · 2.1K citations · Full text
Natural Sciences, Physics, Optics +15
Single-chip microprocessor that communicates directly using light
Chen Sun, Mark T. Wade, Yunsup Lee et al. · Nature · 2015 · 1.3K citations · Full text