Hardware-aware efficient neural network design system having differentiable neural architecture search
US11748615B1 · kind B1 · utility
Assignee
Inventors
Key dates
| Filing date | Dec 5, 2019 |
| Grant date | Sep 5, 2023 |
| Priority date | — |
| Expiry date | Jul 5, 2042 |
Classification
- Technology area (CPC G)Physics
- CPC primaryG06N3/084
- WIPO fieldComputer technology
- WIPO sectorElectrical engineering
Abstract
Computer implemented systems are described that implement a differentiable neural architecture search (DNAS) engine executing on one or more processors. The DNAS engine is configured with a stochastic super net defining a layer-wise search space having a plurality of candidate layers, each of the candidate layers specifying one or more operators for a neural network architecture. Further, the DNAS engine is configured to process training data to train weights for the operators in the stochastic super net based on a loss function representing a latency of the respective operator on a target platform, and to select a set of candidate neural network architectures from the trained stochastic super net. The DNAS engine may, for example, be configured to train the stochastic super net by traversing the layer-wise search space using gradient-based optimization of network architecture distribution.
Source: USPTO / EPO open patent data. Objective bibliographic and citation counts.