Patents
US 12762391 B2: Scale-, shift-, and rotation-invariant diffractive optical networks
- Granted
- 2026-10-13
- Filed
- 2021-10-22 application 18249726
- Type
- Utility · 20 claims
- Elsewhere
- Google Patents ↗ · USPTO patent document ↗ · USPTO Patent Center record ↗
Abstract
A method of forming an optical neural network for processing an input object image or optical signal that is invariant to object transformations includes training a software-based neural network model to perform one or more specific optical functions for a multi-layer optical network having physical features located in each of the layers of the optical neural network. The training includes feeding different input object images or optical signals that have random transformations or shifts and computing at least one optical output of optical transmission and/or reflection through the optical neural network using an optical wave propagation model and iteratively adjusting transmission/reflection coefficients for each layer until optimized transmission/reflection coefficients are obtained. A physical embodiment of the optical neural network is then made that has a plurality of substrate layers having physical features that match the optimized transmission/reflection coefficients obtained by the trained neural network model.
Source: PTBLXML, file of 2026-10-13 (ipgb20261013.xml).
Assignees
| Assignee | Type | Place | Also on furp.org | Source |
|---|---|---|---|---|
| THE REGENTS OF THE UNIVERSITY OF CALIFORNIA 8,781 patents | US company or organization | Oakland, CA | REGENTS OF THE UNIVERSITY OF CALIFORNIA State business registration FUZZY medium confidence: same name (legal endings aside) and state | PTBLXML, file of 2026-10-13 |
Inventors
| Inventor | Place | Patents | Person page | Source |
|---|---|---|---|---|
| Aydogan Ozcan | Los Angeles, CA | 74 | PTBLXML, file of 2026-10-13 | |
| Deniz Mengu | Los Angeles, CA | 10 | PTBLXML, file of 2026-10-13 | |
| Yair Rivenson | Los Angeles, CA | 22 | PTBLXML, file of 2026-10-13 |
CPC categories
| Subclass | Category | First group | Source |
|---|---|---|---|
| G06N | Computing arrangements based on specific computational models | G06N3/067 | PTBLXML, file of 2026-10-13 |
| G02B | Optical elements, systems or apparatus | G02B1/002 | PTBLXML, file of 2026-10-13 |
Cooperative Patent Classification, as currently assigned (one row per subclass).
Assignments and security interests
No recorded assignments or security interests on file for this patent.
USPTO bulk data: PatentsView granted patents, disambiguated (PVGPATDIS) for patents, assignees, inventors, places and CPC categories; the USPTO Patent Assignment Dataset (ECORSEXC) for assignments and security interests. Patents filed in the last 20 years. No claims or full text. Links to other records are by name (and state): EXACT means the identical full name and state; FUZZY means a looser name match, with the confidence shown.