Celestial Ai Inc.

Aristotle University of Thessaloniki-research Committee E.l.k.e

Amo Gmbh Gesellschaft Für Angewandte Mikro- Und Optoelektronic MIT Beschränkter Haftung

Gesellschaft Fur Angewandte Mikro- Und Optoelektronik MIT Beschrankter Haftung - Amo Gmbh

Aristotle University of Thessaloniki - E.l.k.e., Research Committee

Nikolaos Pleros

Apostolos Tsakyridis

Angelina Totovic

David E Lazovsky

Georgios Giamougiannis

George Giamougiannis

Angelina Totović

Yangjin Ma

Philip Winterbottom

Martinus Bos

Georgios Ntampos

Dimitra Ketzaki

Anastasios Tefas

Anna-Lena Giesecke

Konstantinos Vyrsokinos

Dimitrios Tsiokos

George Mourgias-Alexandris

Nikolaos Passalis

Anna Lena Giesecke

The present disclosure relates to implementations of a photonic circuit, and particularly to a photonic circuit that includes one or more matrix circuits. For example, the present disclosure relates to photonic circuit implementations of unitary matrices, and of arbitrary real and/or complex matrices factorized using unitary matrices, that utilize special generalized Mach-Zehnder interferometers (SGMZIs) as building blocks of various matrix circuit architectures.

Fidelity-restorable photonic linear operator

Neuromorphic computing can employ coherent linear optical neurons implemented with multipath optical interferometers in which optical amplitude modulators and phase shifters impart neuron input signals and neuron weights onto optical carrier signals that are then summed at the interferometer output. Photodetectors at the interferometer output, optionally in conjunction with preceding nonlinear optical circuits, may implement a non-linear activation function and generate electronic neuron output signals that can be provided as input to other optical neurons to form an optical neural network.

Neuromorphic photonics with coherent linear neurons

Disclosed are coherent photonic circuit architectures that optically implement linear algebraic computations. In neuromorphic applications of such photonic circuit architectures, individual neural network layers can be implemented by coherent optical linear neurons in a crossbar configuration, integrated with electronic circuitry at the interfaces between neural network layers to determine the neuron inputs to one layer based on the neuron outputs of the preceding layer. Wavelength division multiplexing can be used to efficiently implement certain specific network models, optionally in conjunction with electro-optic switches to render a generic hardware configuration programmable.

Coherent photonic computing architectures

Vector and matrix multiplications can be accomplished in photonic circuitry by coherently combining light that has been optically modulated, in amplitude and/or phase, in accordance with the vector and matrix components. Disclosed are various beneficial photonic circuit layouts characterized by loss- and delay-balanced optical paths. In various embodiments, loss balancing across paths is achieved with suitable optical coupling ratios and balanced numbers of waveguide crossings (using dummy crossings where needed) across the paths. Delays are balanced in some embodiments with geometrically delay-matched optical paths.

Balanced photonic architectures for matrix computations

The invention relates to a device comprising a first optical Mach-Zehnder interferometric sensor (MZI1) with a large FSR, wherein a plasmonic waveguide () thin-film or hybrid slot, is incorporated as transducer element planar integrated on Si3N4 photonic waveguides and a second optical interferometric Mach-Zehnder (MZI2), both comprising thermo-optic phase shifters () for optimally biasing said MZI sensor (MZI1) and MZI as variable optical attenuator VOA. It further comprises an overall chip (), being remarkable in that it comprises a set of Photonic waveguides () with a high index silicon nitride strip (), which is sandwiched between a low index oxide substrate (SiO2) and a low index oxide superstrate (LTO); Optical coupling structures () at both ends of the sensor acting as the optical I/Os; an Optical splitter () and an optical combiner () for optical splitting at the first junction () of said first sensor (MZI1) and optical combining at the second junction () of said first MZI (MZI1); a variable optical attenuator (VOA) with said additional second MZI (MZI2), which is nested into said MZI1 (sensor)), deploying an optical splitter and an optical combiner for optical splitting at the first junction of said additional second MZI (MZI2), and optical combining at the second junction of said second MZI (MZI2); a set of Thermo-optic phase shifters () to tune the phase of the optical signal in the reference arm () of each said MZI (MZI1, MZI2-VOA); wherein Thermo-optic phase shifters are formed by depositing two metallic stripes parallel to each other on top of a section of the photonic waveguide and along the direction of propagation of light; and a plasmonic waveguide () in the upper branch () of said first MZI (MZI1), that confines light propagation through coupling to Surface Plasmon Polaritons (SPP) at the metal-analyte interface, and method associated thereto.

Integrated plasmo-photonic biosensor and method of use

Growing community of inventors

Salonika, Greece

Nikolaos Pleros