Deep learning model training system
US10769528B1 · kind B1 · utility
Assignee
Inventors
Key dates
| Filing date | Oct 2, 2019 |
| Grant date | Sep 8, 2020 |
| Priority date | — |
| Expiry date | Oct 2, 2039 |
Classification
- Technology area (CPC G)Physics
- CPC primaryG06N3/045
- WIPO fieldComputer technology
- WIPO sectorElectrical engineering
Abstract
A computer trains a neural network model. (B) A neural network is executed to compute a post-iteration gradient vector and a current iteration weight vector. (C) A search direction vector is computed using a Hessian approximation matrix and the post-iteration gradient vector. (D) A step size value is initialized. (E) An objective function value is computed that indicates an error measure of the executed neural network. (F) When the computed objective function value is greater than an upper bound value, the step size value is updated using a predefined backtracking factor value. The upper bound value is computed as a sliding average of a predefined upper bound updating interval value number of previous upper bound values. (G) (E) and (F) are repeated until the computed objective function value is not greater than the upper bound value. (H) An updated weight vector is computed to describe a trained neural network model.
Source: USPTO / EPO open patent data. Objective bibliographic and citation counts.