Deep learning enabled design of complex transmission matrices for universal optical components

Abstract

Recent breakthroughs in photonics-based quantum, neuromorphic and analogue processing have pointed out the need for new schemes for fully programmable nanophotonic devices. Universal optical elements based on interferometer meshes are underpinning many of these new technologies, however this is achieved at the cost of an overall footprint that is very large compared to the limited chip real estate, restricting the scalability of this approach. Here, we consider an ultracompact platform for low-loss programmable elements using the complex transmission matrix of a multi-port multimode waveguide. We propose a deep learning inverse network approach to design arbitrary transmission matrices using patterns of weakly scattering perturbations. The demonstrated technique allows control over both the intensity and phase in a multiport device at a four orders reduced device footprint compared to conventional technologies, thus opening the door for large-scale integrated universal networks.

13 pages, 6 figures + supporting information pdf

References in corpus (29)

• Deep Learning with Coherent Nanophotonic Circuits
• An Introduction to Variational Autoencoders
• Measuring the Transmission Matrix in Optics : An Approach to the Study and Control of Light Propagation in Disordered Media
• Integrated Photonic Quantum Technologies
• Training deep neural networks for the inverse design of nanophotonic structures
• Inverse design and demonstration of a compact and broadband on-chip wavelength demultiplexer
• Phase recovery and holographic image reconstruction using deep learning in neural networks
• Light fields in complex media: mesoscopic scattering meets wave control
• Don't Decay the Learning Rate, Increase the Batch Size
• Deep neural networks for the evaluation and design of photonic devices
• Quantum transport simulations in a programmable nanophotonic processor
• Learning to see through multimode fibers
• Wave Physics as an Analog Recurrent Neural Network
• Nanophotonic Computational Design
• Deep learning approach based on dimensionality reduction for designing electromagnetic nanostructures
• All passive photonic power divider with arbitrary split ratio
• Evolutionary optimization of optical antennas
• Evolutionary Multi-Objective Optimisation of Colour Pixels based on Dielectric Nano-Antennas
• Pushing the limits of optical information storage using deep learning
• Enhanced Light-Matter Interactions in Dielectric Nanostructures via Machine Learning Approach
• Deep Learning Reveals Underlying Physics of Light-matter Interactions in Nanophotonic Devices
• Elucidating the Behavior of Nanophotonic Structures Through Explainable Machine Learning Algorithms
• An all-optical spatial light modulator for field-programmable silicon photonic circuits
• Ultrafast Photomodulation Spectroscopy: a device-level tool for characterizing the flow of light in integrated photonic circuits
• Probability-Density-Based Deep Learning Paradigm for the Fuzzy Design of Functional Metastructures
• Shaping the Branched Flow of Light through Disordered Media
• Ultrafast perturbation maps as a quantitative tool for testing of multi-port photonic devices
• Progressive-Growing of Generative Adversarial Networks for Metasurface Optimization
• Simultaneous inverse design of materials and parameters of core-shell nanoparticle via deep-learning: Demonstration of dipole resonance engineering

Cited by in corpus (17)

• Customized anti-reflection structure for perfect transmission through complex media
• A newcomer's guide to deep learning for inverse design in nano-photonics
• Inverse-design of high-dimensional quantum optical circuits in a complex medium
• Manifold Learning for Knowledge Discovery and Intelligent Inverse Design of Photonic Nanostructures: Breaking the Geometric Complexity
• Deep learning enabled strategies for modelling of complex aperiodic plasmonic metasurfaces of arbitrary size
• Reflectionless Programmable Signal Routers
• Inverse design of nano-photonic wavelength demultiplexer with a deep neural network approach
• Inverse design with flexible design targets via deep learning: Tailoring of electric and magnetic multipole scattering from nano-spheres
• Waveguide lattice based architecture for multichannel optical transformations
• Programmable metasurfaces for future photonic artificial intelligence
• Universal linear optics by programmable multimode interference
• Deep learning for nano-photonic materials -- The solution to everything!?
• Inverse Design of Unitary Transmission Matrices in Silicon Photonic Coupled Waveguide Arrays using a Neural Adjoint Model
• Non-volatile programmable silicon photonics using an ultralow loss Sb${}_2$Se${}_3$ phase change material
• Fast multi-channel inverse design through augmented partial factorization
• On-chip rewritable phase-change metasurface for programmable diffractive deep neural networks
• PyMieDiff: A differentiable Mie scattering library