Deep neural networks training for speech and pattern recognition
US9477925B2 · kind B2 · utility
Assignee
Inventors
Key dates
| Filing date | Nov 20, 2012 |
| Grant date | Oct 25, 2016 |
| Priority date | — |
| Expiry date | Jun 24, 2034 |
Classification
- Technology area (CPC G)Physics
- CPC primaryG10L15/06
- WIPO fieldComputer technology
- WIPO sectorElectrical engineering
Abstract
The use of a pipelined algorithm that performs parallelized computations to train deep neural networks (DNNs) for performing data analysis may reduce training time. The DNNs may be one of context-independent DNNs or context-dependent DNNs. The training may include partitioning training data into sample batches of a specific batch size. The partitioning may be performed based on rates of data transfers between processors that execute the pipelined algorithm, considerations of accuracy and convergence, and the execution speed of each processor. Other techniques for training may include grouping layers of the DNNs for processing on a single processor, distributing a layer of the DNNs to multiple processors for processing, or modifying an execution order of steps in the pipelined algorithm.
Source: USPTO / EPO open patent data. Objective bibliographic and citation counts.