Provided is an optical signal processing device capable of improving computing accuracy without increasing the number of nodes of a reservoir layer. An optical signal processing device for converting an input one-dimensional signal to an optical signal and performing signal processing includes an input unit configured to perform linear processing on the input one-dimensional signal to convert the one-dimensional signal to an optical signal, a reservoir unit connected to an output of the input unit and configured to perform linear processing and nonlinear processing on the optical signal, an output unit connected to an output of the reservoir unit and configured to convert the optical signal to an electrical signal, perform linear processing to output a one-dimensional output, and a determination unit configured to determine whether the one-dimensional output from the output unit is to be output or to be input as the one-dimensional signal to the input unit.

An apparatus includes a plurality of interconnected reconfigurable beam splitters and a plurality of phase shifters collectively configured to define a network of optical devices. The network of optical devices is configured to perform a universal transformation on a plurality of input optical signals via a triangular architecture. The apparatus also includes a first delay line optically coupled to the network of optical devices and configured to send at least one output optical signal from a plurality of output optical signals of the network of optical devices to interact with at least one input optical signal in the plurality of input optical signals within the network of optical devices.

Photonic processors are described. The photonic processors described herein are configured to perform matrix-matrix (e.g., matrix-vector) multiplication. Some embodiments relate to photonic processors arranged according to a dual-rail architecture, in which numeric values are encoded in the difference between a pair optical signals (e.g., in the difference between the powers of the optical signals). Relative to other architectures, these photonic processors exhibit increased immunity to noise. Some embodiments relate to photonic processors including modulatable detector-based multipliers. Modulatable detectors are detectors designed so that the photocurrent can be modulated according to an electrical control signal. Photonic processors designed using modulatable detector-based multipliers are significantly more compact than other types of photonic processors.

Photonic processors are described. The photonic processors described herein are configured to perform matrix-matrix (e.g., matrix-vector) multiplication. Some embodiments relate to photonic processors arranged according to a dual-rail architecture, in which numeric values are encoded in the difference between a pair optical signals (e.g., in the difference between the powers of the optical signals). Relative to other architectures, these photonic processors exhibit increased immunity to noise. Some embodiments relate to photonic processors including modulatable detector-based multipliers. Modulatable detectors are detectors designed so that the photocurrent can be modulated according to an electrical control signal. Photonic processors designed using modulatable detector-based multipliers are significantly more compact than other types of photonic processors.

An apparatus includes a first optical circuit and a second optical circuit. The first optical circuit has a network of interconnected interferometers to perform an M-mode universal transformation on N input optical modes that are divided into (M−1) groups of pulses. The first optical circuit also includes M input ports. Each input port of a first (M−1) input ports is configured to receive a corresponding group of pulses in the (M−1) groups of pulses. The first optical circuit also includes M output ports and a first delay line to couple an Mth output port with an Mth input port. The second optical circuit includes a network of beamsplitters and swap gates to perform a (2M−3)-mode residual transformation. The first optical circuit and the second optical circuit are configured to perform an arbitrary N-mode unitary transformation to the N input optical modes via a rectangular architecture.

A method includes calculating a plurality of permutation matrices of an input matrix that characterizes a linear transformation of a plurality of input states. The method also includes determining a plurality of settings of an optical circuit based on the plurality of permutation matrices. Each setting in the plurality of settings is associated with an electric power, from a plurality of electric powers, consumed by the optical circuit. The method also includes determining a selected setting of the optical circuit based on the electric power from the plurality of electric powers and consumed by the optical circuit at each setting from the plurality of settings associated with the electric power. The method further includes implementing the selected setting on the optical circuit to perform the linear transformation of the plurality of input states.

Embodiments of the present disclosure are directed toward techniques and configurations for a photonics integrated circuit (IC) for an optical neural network (ONN). In embodiments, the photonics IC includes monolithically optoelectronic components in a single semiconductor substrate including a combination of one or more of integrated array of light sources, a plurality of optical modulators, an optical unitary matrix multiplier, non-linear optical amplifiers or attenuators, and a plurality of photodetectors. In embodiments, the optical unitary matrix multiplier comprises a plurality of 22 unitary optical matrices optically interconnected, wherein each 22 unitary optical matrix comprises a plurality of phase shifters. In embodiments, each 22 unitary optical matrix is to phase shift, split, and/or combine one or more of the optical signal inputs. Other embodiments may be described and/or claimed.

The Ising model calculation device selects a solution having a consistent quality from among solutions obtained through the calculations with the evaluation index of a calculation accuracy. A coupling coefficient obtained by combining the Ising model coupling coefficient corresponding to a problem for which a solution should be calculated with the Ising model coupling coefficient corresponding to the check problem is set as a coupling coefficient used to calculate the interaction. With regard to a calculation value corresponding to the check spin among the calculation values using a plurality of light pulses, the compatibility as the solution of the check problem is judged. When the judgement result shows the compatibility as the solution of the check problem, a calculation value other than the calculation values corresponding to the check spin among the resultant calculation values is outputted as a solution to the problem for which a solution should be calculated.

Embodiments of the present disclosure describe techniques and configurations for a nonlinear optical device used to construct an optical neural network (ONN) with an arbitrary number of layers of matrix multipliers. The nonlinear optical device includes a waveguide to receive optical input and a gain medium coupled with the waveguide, to amplify or attenuate the received optical input, to provide an output that is amplified in a nonlinear manner in response to the optical input reaching saturation, where the nonlinearly amplified output is to provide a nonlinear activation function for an ONN. Additional embodiments may be described and claimed.

Embodiments are disclosed for computing an eye diagram based on input pulse responses. An example method includes receiving a set of input pulse responses in one or more unit interval (UI) spaced samples. The set of input pulse responses is generated based on measuring a signal histogram of a receiver of a pulse amplitude modulation analog signal. The method further includes receiving a set of voltage range constraints and generating a matrix based at least in part on an element-wise trigonometric-based operation performed on one or more products of each element of the set of input pulse responses and the set of voltage range constraints. The method further includes generating an eye diagram probability density function based on the matrix and computing an eye diagram based on the eye diagram probability density function, the voltage range constraints, and time data associated with the one or more unit interval spaced samples.