# US 2022/0034824 A1 · Space-time scattering network for inverse design and tomography

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

- Number: US 2022/0034824 A1
- Document ID: US20220034824A1
- Status: Published application
- Kind: A1
- Application number: 17/279,453
- Filed: 2019-09-26
- Published: 2022-02-03
- Earliest claimed: 2018-09-26
- Assignees: Northwestern University
- Applicants: Northwestern University
- Inventors: Hooman Mohseni; Travis G. Hamilton
- Web page: https://patentgrep.com/patent/US20220034824A1

## CPC

- G01N 23/046: using tomography, e.g. computed tomography [CT]
- G06N 3/08: Learning methods
- G01R 33/54: Signal processing systems, e.g. using pulse sequences {; Generation or control of pulse sequences; Operator console}
- G01R 33/56: Image enhancement or correction, e.g. subtraction or averaging techniques {, e.g. improvement of signal-to-noise ratio and resolution}
- G02B 3/00: Simple or compound lenses
- G06N 3/045: Combinations of networks
- G06N 3/049: Temporal neural networks, e.g. delay elements, oscillating neurons or pulsed inputs
- G06N 3/09: Supervised learning
- G06T 12/20: Inverse problem, i.e. transformations from projection space into object space
- G06N 3/067: using optical means
- G06N 3/105: {Shells for specifying net layout}
- G01N: INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES (measuring or testing apparatus or processes other than immunoassay, involving enzymes or microorganisms C12M, C12Q)
- G06N: COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G01R: MEASURING ELECTRIC VARIABLES; MEASURING MAGNETIC VARIABLES (indicating correct tuning of resonant circuits H03J3/12)
- G02B: OPTICAL ELEMENTS, SYSTEMS OR APPARATUS
- G06T: IMAGE DATA PROCESSING OR GENERATION, IN GENERAL

## Abstract

A system to generate a space-time scattering network includes a computing unit configured to store a space-time scattering network (STSN) algorithm. The computing unit also executes the STSN algorithm to represent scattering of light through a material mathematically as a tensor field at a location. The computing unit also generates a subnet that represents the tensor field at the location. The computing unit also identifies, based on a translation operator, connections between a plurality of subnets, where each of the subnets in the plurality of subnets represents a given tensor field at a given location. The computing unit also forms the STSN based at least in part on the identified connections between the plurality of subnets. The computing unit further uses the STSN to inversely design an optical component or to perform tomography.

## Claims

### Claim 1

A system to generate a space-time scattering network, the system comprising:
a computing unit configured to:
store a space-time scattering network (STSN) algorithm; and
execute the STSN algorithm to represent scattering of light through a material mathematically as a tensor field at a location;
generate a subnet that represents the tensor field at the location;
identify, based on a translation operator, connections between a plurality of subnets, wherein each of the subnets in the plurality of subnets represents a given tensor field at a given location;
form the STSN based at least in part on the identified connections between the plurality of subnets; and
use the STSN to inversely design a material to have a specific response to electromagnetic radiation or to perform tomography.

### Claim 2 (depends on 1)

The system of claim 1, wherein the location of the tensor field is given by a position vector.

### Claim 3 (depends on 1)

The system of claim 1, wherein the tensor field couples an incoming tensor field and an outgoing tensor field at the location.

### Claim 4 (depends on 1)

The system of claim 1, wherein the tensor field is based on optical properties of the material.

### Claim 5 (depends on 1)

The system of claim 1, wherein the translation operator defines a temporal connection between the plurality of subnets.

### Claim 6 (depends on 1)

The system of claim 1, wherein the computing unit includes hardware and software, and wherein the hardware, the software, or a combination of the hardware and the software is configured to form the STSN as a neural network.

### Claim 7 (depends on 6)

The system of claim 6, wherein a number of unknown weights in the neural network is equal to a number of unknown optical parameters in a design space of the system.

### Claim 8 (depends on 1)

The system of claim 1, wherein the subnet represents optical properties of the material at the location, and wherein the location comprises a point in space.

### Claim 9 (depends on 8)

The system of claim 8, wherein one or more weights associated with the subnet are based on a refractive index of the material.

### Claim 10 (depends on 9)

The system of claim 9, wherein the one or more weights change over time as the refractive index changes over time.

### Claim 11

A method for generating a space-time scattering network (STSN), the method comprising:
representing, by a computing unit, scattering of light through a material mathematically as a tensor field at a location;
generating, by the computing unit, a subnet that represents the tensor field at the location;
identifying, by the computing unit and based on a translation operator, connections between a plurality of subnets, wherein each of the subnets in the plurality of subnets represents a given tensor field at a given location;
forming, by the computing unit, the STSN based at least in part on the identified connections between the plurality of subnets; and
using, by the computing unit, the STSN to inversely design an optical component or to perform tomography.

### Claim 12 (depends on 13)

The method of claim 13, further comprising determining the tensor field by coupling an incoming tensor field and an outgoing tensor field at the location.

### Claim 13 (depends on 13)

The method of claim 13, wherein the tensor field is based on optical properties of the material.

### Claim 14 (depends on 13)

The method of claim 13, wherein the translation operator defines a temporal connection between the plurality of subnets.

### Claim 15 (depends on 13)

The method of claim 13, wherein forming the STSN comprises forming the STSN as a neural network.

### Claim 16 (depends on 13)

The method of claim 13, further comprising identifying one or more weights associated with the subnet, wherein the one or more weights are based at least in part on a refractive index of the material.

### Claim 17

A tangible computer-readable medium having computer-readable instructions stored thereon that, upon execution by a processor of a computing system, cause the computing system to:
represent scattering of light through a material mathematically as a tensor field at a location;
generate a subnet that represents the tensor field at the location;
identify, based on a translation operator, connections between a plurality of subnets, wherein each of the subnets in the plurality of subnets represents a given tensor field at a given location;
form a space-time scattering network (STSN) based at least in part on the identified connections between the plurality of subnets; and
use the STSN to inversely design an optical component or to perform tomography.

### Claim 18 (depends on 17)

The tangible computer-readable medium of claim 17, wherein the computer-readable instructions further cause the computing system to determine the tensor field by coupling an incoming tensor field and an outgoing tensor field at the location.

### Claim 19 (depends on 17)

The tangible computer-readable medium of claim 17, wherein the computer-readable instructions further cause the computing system to form the STSN as a neural network.

### Claim 20 (depends on 17)

The tangible computer-readable medium of claim 17, wherein the computer-readable instructions further cause the computing system to identify one or more weights associated with the subnet, wherein the one or more weights are based at least in part on a refractive index of the material.
