Systems and methods for training matrix-based differentiable programs
US10740693B2 · kind B2 · utility
Assignee
Inventors
Key dates
| Filing date | May 14, 2019 |
| Grant date | Aug 11, 2020 |
| Priority date | — |
| Expiry date | May 14, 2039 |
Classification
- Technology area (CPC G)Physics
- CPC primaryG06N20/10
- WIPO fieldComputer technology
- WIPO sectorElectrical engineering
Abstract
Methods and apparatus for training a matrix-based differentiable program using a photonics-based processor. The matrix-based differentiable program includes at least one matrix-valued variable associated with a matrix of values in a Euclidean vector space. The method comprises configuring components of the photonics-based processor to represent the matrix of values as an angular representation, processing, using the components of the photonics-based processor, training data to compute an error vector, determining in parallel, at least some gradients of parameters of the angular representation, wherein the determining is based on the error vector and a current input training vector, and updating the matrix of values by updating the angular representation based on the determined gradients.
Source: USPTO / EPO open patent data. Objective bibliographic and citation counts.