A technology is described for a Photonic Integrated Circuit (PIC) radio frequency (RF) correlator. The PIC RF Correlator can comprise two optical waveguides to receive first and second optical signals that are modulated by first and second RF signals, respectively. Two 1 to M optical splitters can split the first and second RF modulated optical signals. Optical delay lines can delay the M split first RF modulated optical signals. M optical balanced couplers can receive and combine the M first delayed RF modulated optical signals with the M split second RF modulated optical signals. Balanced photodetectors can output a differential integration on the first and second combined RF modulated optical signals. A processor can add the outputs of the M optical balanced photodetectors to form a frequency domain correlated signal of the first and second RF signals.

An optical neural network is constructed based on photonic integrated circuits to perform neuromorphic computing. In the optical neural network, matrix multiplication is implemented using one or more optical interference units, which can apply an arbitrary weighting matrix multiplication to an array of input optical signals. Nonlinear activation is realized by an optical nonlinearity unit, which can be based on nonlinear optical effects, such as saturable absorption. These calculations are implemented optically, thereby resulting in high calculation speeds and low power consumption in the optical neural network.

An optical neural network is constructed based on photonic integrated circuits to perform neuromorphic computing. In the optical neural network, matrix multiplication is implemented using one or more optical interference units, which can apply an arbitrary weighting matrix multiplication to an array of input optical signals. Nonlinear activation is realized by an optical nonlinearity unit, which can be based on nonlinear optical effects, such as saturable absorption. These calculations are implemented optically, thereby resulting in high calculation speeds and low power consumption in the optical neural network.

Methods, devices, and systems for processing information are disclosed. An example device may comprise a metastructure comprising a plurality of physical features configured to transform an analog signal according to a kernel of an integral equation. The device may comprise one or more waveguides coupled to the metastructure and configured to recursively supply a transformed analog output signal of the metastructure to an input of the metastructure to iteratively cause one or more transformed analog signals output from the metastructure to converge to an analog signal representing a solution to the integral equation.

An optical processor. In some embodiments, the optical processor includes a free propagation region; a plurality of input waveguides, coupled to an input aperture of the free propagation region; a plurality of output waveguides, coupled to an output aperture of the free propagation region; a first modulator, on one of the input waveguides; and an optical detector, on one of the output waveguides.

An optical processor. In some embodiments, the optical processor includes a free propagation region; a plurality of input waveguides, coupled to an input aperture of the free propagation region; a plurality of output waveguides, coupled to an output aperture of the free propagation region; a first modulator, on one of the input waveguides; and an optical detector, on one of the output waveguides.

A method to incorporate multiple independent optical correlators into one system. By independent optical correlator, we mean an optical correlator comprising of an input SLM, filter SLM, and camera, combined with appropriate coherent illumination and Fourier transforming lenses. By one system we mean a single optical system which utilises the elements of each of the independent correlators multiple times.

An optical neural network is constructed based on photonic integrated circuits to perform neuromorphic computing. In the optical neural network, matrix multiplication is implemented using one or more optical interference units, which can apply an arbitrary weighting matrix multiplication to an array of input optical signals. Nonlinear activation is realized by an optical nonlinearity unit, which can be based on nonlinear optical effects, such as saturable absorption. These calculations are implemented optically, thereby resulting in high calculation speeds and low power consumption in the optical neural network.

A technology is described for a Photonic Integrated Circuit (PIC) radio frequency (RF) in-phase quadrature phase (I/O) correlator. The PIC RF Correlator can comprise two optical waveguides to receive first and second optical signals that are modulated by first and second RF signals, respectively. Two 1 to M optical splitters can split the first and second RF modulated optical signals. Optical delay lines can delay the M split first RF modulated optical signals. M optical balanced couplers can receive and combine the M first delayed RF modulated optical signals with the M split second RF modulated optical signals. Balanced photodetectors can output a differential integration on the first and second combined RF modulated optical signals for in-phase and quadrature phase signals. A processor can add the outputs of the M optical balanced photodetectors to form a frequency domain correlated signal of the first and second RF signals with real and imaginary parts.

The present invention provides optical computing by means of fast Fourier transform Integration on Silicon On Insulator chip technology with implementation in the analog and temporal domain. This is done by cascading (N2) stages of delayed interferometers (couplers and phase shifters) where a parallel set of N time samples are taken and using the delay lines and phase of the optical components (constructive/deconstructive interference) the DFT is computed. The Optical Fast Fourier Transform (OFFT) design was built on passive components (22 couplers: cascaded Mach Zehnder Interferometer) used for addition and subtraction through optical interference, waveguides with short path differences are used for phase shifting and waveguides with long path differences are used for signal delay based on the needed number of outputs. Since the OFFT is a system of imbalanced interferometers, there are additional bends designed to compensate for the difference in power ratios of the arms.