Systems and methods that include: providing input information in an electronic format; converting at least a part of the electronic input information into an optical input vector; optically transforming the optical input vector into an optical output vector based on an optical matrix multiplication; converting the optical output vector into an electronic format; and electronically applying a non-linear transformation to the electronically converted optical output vector to provide output information in an electronic format.

In some examples, a set of multiple input values are encoded on respective optical signals carried by optical waveguides. For each of at least two subsets of one or more optical signals, a corresponding set of one or more copying modules splits the subset of one or more optical signals into two or more copies of the optical signals. For each of at least two copies of a first subset of one or more optical signals, a corresponding multiplication module multiplies the one or more optical signals of the first subset by one or more matrix element values using optical amplitude modulation. For results of two or more of the multiplication modules, a summation module produces an electrical signal that represents a sum of the results of the two or more of the multiplication modules.

An optical information processing system comprising a nonlinear element selected in relation to input optical pulses to initiate nonlinear optical frequency conversion and a detection unit, the nonlinear element receiving encoded information input in form of pulsed light, pulsed light from the nonlinear element being read-out by the detection unit for spectro-temporal feature extraction, and the readout being used to train the system on a specific target to obtain a task-specific output or re-directed to the nonlinear element to obtain an input-dependent output, yielding processed information comprising selective positions in an output of the system. A method for training an optical system comprises, for each individual optical input information, reading specific optical amplitude or phase features from specific output bins of the system in time or frequency, weighting and evaluating the specific features towards optimizing user-defined fitness function to identify, classify, or fit the input information.

The present disclosure relates to a field of photonic computing and provides a photonic computing system including: a photonic computing unit configured to receive a first plurality of optical signals, wherein the first plurality of the optical signals represent a first set of values respectively. The photonic computing unit includes a plurality of weight modules, the weight modules represent a plurality of predetermined values respectively, and each of the weight modules corresponds to one of the predetermined values. Each of the weight modules includes: an optical input part configured to receive one optical signal of the first plurality of the optical signals, and at least one directional coupler. The weight module corresponds to one of the predetermined values to achieve the multiplication operation.

A purely optical XOR gate is disclosed, implemented entirely within fiber optic channels and without any electrical control elements. Two digital data light inputs, A and B, are each amplified, split, and partially converted to higher-frequency control light via frequency doublers. The control light from each input is directed into a corresponding right-angle Data Light Extinguisher (DLE) intersecting the opposite channel, where it extinguishes simultaneous 1 pulses by inducing a waveguide cutoff through piezoelectric deformation. The remaining data light pulses, representing conditions where only A or only B is high, are combined into a single output channel. This architecture operates in parallel optical paths without reflections or high voltage, enabling high-speed, low-loss XOR logic entirely in the photonic domain.