# US 2025/0028949 A1 · Optical neural network with gain from parity time optical couplers

> Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt

- Number: US 2025/0028949 A1
- Document ID: US20250028949A1
- Status: Published application
- Kind: A1
- Application number: 18/711,483
- Filed: 2022-11-18
- Published: 2025-01-23
- Earliest claimed: 2021-11-18
- Assignees: University of Southern California
- Applicants: University of Southern California
- Inventors: Mercedeh KHAJAVIKHAN; Haoqin DENG
- Web page: https://patentgrep.com/patent/US20250028949A1

## CPC

- G06N 3/067: using optical means
- G06N 3/084: Backpropagation, e.g. using gradient descent
- G06N 3/09: Supervised learning
- G06N: COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS

## Abstract

An apparatus and methods are provided for an optical neural network architecture that utilizes parity-time (PT) symmetric couplers. The example PT symmetric optical neural network is based on layers using the PT symmetric couplers that each have two parallel waveguides. One waveguide applies gain while the other waveguide applies an equal loss to signals.

## Claims

### Claim 1

A method for implementing a first layer of an optical neural network (ONN), the method comprising:
encoding pixels of incoming data in light amplitude;
sending optical signals corresponding to the encoded pixels to a first parity-time (PT) coupler;
causing the optical signals passing through the first PT coupler to pass through an amplifier/attenuator;
passing the signals through a second PT coupler; and
passing optical signals to nonlinear elements (NE).

### Claim 2 (depends on 1)

The method of claim 1, wherein the light amplitude is provided by a series of laser sources/beams wherein the pixels are encoded by lasers.

### Claim 3 (depends on 1)

The method of claim 1, further comprising modulating the data on a carrier frequency prior to sending optical signals to the first PT coupler.

### Claim 4 (depends on 1)

The method of claim 1, wherein the method is performed on a parity time-symmetric optical neural network (PT-ONN) having a first layer and a second layer, wherein the first layer includes the first and second PT couplers in a symmetrical arrangement.

### Claim 5 (depends on 1)

The method of claim 1, wherein the first PT coupler and the second PT coupler each include a first waveguide experiencing gain and a second waveguide experiencing an equal amount of loss.

### Claim 6 (depends on 5)

The method of claim 5, wherein the first and second PT couplers are fabricated from III-V semiconductor materials on a silicon-on-insulator chip, and wherein the waveguides are fabricated using quantum well intermixing to change the refractive index of the III-V materials.

### Claim 7

(canceled)

### Claim 8

(canceled)

### Claim 9 (depends on 4)

The method of claim 4, wherein:
the encoding pixels comprises encoding N1 pixels in the first layer such that the optical signals pass through the first PT coupler and the second PT coupler and encounter the nonlinear elements;
the first PT coupler is one of a triangular-shaped array of (N1(N1−1)/2) PT-symmetric directional couplers;
the second PT coupler is one of a triangular-shaped array of (N2(N2−1)/2) PT-symmetric directional couplers;
the amplifier/attenuator comprises N2 amplifiers/attenuators; and
the NE comprise N2 nonlinear elements; and wherein N1 is a size of an input layer and N2 is a size of the second layer, wherein the second layer is a hidden layer.

### Claim 10 (depends on 9)

The method of claim 9, wherein the method further comprising:
encoding N2 pixels of incoming data in light amplitude;
sending a second set of optical signals corresponding to the encoded N2 pixels to a third PT coupler that is in a triangular-shaped array of (N2(N2−1)/2) PT-symmetric directional couplers in the second layer; and
causing the second set of optical signals passing through the third PT coupler to pass through one of N3 amplifier/attenuators and then a fourth PT coupler that is in a triangular-shaped array of (N3(N3−1)/2) PT-symmetric directional couplers, the second set of optical signals fed into N3 optical detectors, wherein N3 is a size of an output layer.

### Claim 11 (depends on 10)

The method of claim 10, wherein a sigmoid activation function is used for the second layer.

### Claim 12 (depends on 10)

The method of claim 10, further comprising training the first layer including sending an output of the optical detectors to an electronic circuit to calculate PT-coupler gain/loss coefficients in training cycles for the first layer.

### Claim 13 (depends on 12)

The method of claim 12, further comprising implementing a gradient descent algorithm in the training cycles using the calculated PT-coupler gain/loss coefficients.

### Claim 14

An optical neural network (ONN) comprising:
a light source configured to encode pixels of incoming data in light amplitude;
a first layer including:
a first parity-time (PT)-symmetric directional coupler configured to receive optical signals corresponding to the encoded pixels;
an amplifier/attenuator configured to receive the optical signals passing through the first PT coupler;
a second PT-symmetric directional coupler configured to receive the optical signals passing through the first PT coupler and the amplifier/attenuator;
nonlinear elements configured to receive the optical signals passing through the first PT coupler, the amplifier/attenuator, and the second PT-symmetric directional coupler in the first layer of the ONN;
a second layer including:
photodetectors configured to receive the optical signals from the first layer of the ONN,
a first parity-time (PT)-symmetric directional coupler configured to receive optical signals from the photodetectors;
an amplifier/attenuator configured to receive the optical signals passing through the first PT coupler;
a second PT-symmetric directional coupler configured to receive the optical signals passing through the first PT coupler and the amplifier/attenuator;
nonlinear elements configured to receive the optical signals passing through the first PT coupler, the amplifier/attenuator, and the second PT-symmetric directional coupler in the second layer of the ONN; and
an output layer of optical detectors.

### Claim 15 (depends on 14)

The optical neural network of claim 14, wherein:
the first layer constitutes an input layer having a size of N1 the second layer constitutes a hidden layer having a size of N2 and the optical detectors constitute an output layer having a size of N3,
the first PT-symmetric directional coupler is one of an array of (N1(N1−1)/2) PT-symmetric directional couplers;
the amplifier attenuator and optical detectors are one of N2 amplifier/attenuators and optical detectors,
the second PT-symmetric directional coupler, and the photodetectors in the second layer are (N2(N2−1)/2), N3, (N3(N3−1)/2), and N3, respectively, and

### Claim 16 (depends on 14)

The optical neural network of claim 14, wherein the light source is a series of laser sources, wherein the pixels are encoded by lasers.

### Claim 17 (depends on 14)

The optical neural network of claim 14, further comprising a laser modulator modulating the data on a carrier frequency prior to sending optical signals to the first PT coupler.

### Claim 18 (depends on 14)

The optical neural network of claim 14, wherein the PT couplers each include a first waveguide experiencing gain and a second waveguide experiencing an equal amount of loss.

### Claim 19 (depends on 18)

The optical neural network of claim 18, wherein the PT couplers are fabricated from III-V semiconductor materials fabricated on a silicon-on-insulator chip.

### Claim 20 (depends on 18)

The optical neural network of claim 18, wherein the waveguides are fabricated using quantum well intermixing to change the refractive index of the III-V semiconductor materials.

### Claim 21

(canceled)

### Claim 22 (depends on 21)

The optical neural network of claim 21, wherein the PT couplers of the first and second layers are fabricated on the silicon through an epitaxial regrowth process.

### Claim 23 (depends on 14)

The optical neural network of claim 14, wherein the neural network is trained via implementing a gradient descent algorithm in training cycles using PT-coupler gain/loss coefficients.
