Neural network architecture using convolution engines
US12050986B2 · kind B2 · utility
Assignee
Inventor
Key dates
| Filing date | Feb 1, 2023 |
| Grant date | Jul 30, 2024 |
| Priority date | — |
| Expiry date | Feb 1, 2043 |
Classification
- Technology area (CPC G)Physics
- CPC primaryG06N3/045
- WIPO fieldComputer technology
- WIPO sectorElectrical engineering
Abstract
Hardware for implementing a Deep Neural Network (DNN) having a convolution layer. A plurality of convolution engines are each operable to perform a convolution operation by applying a filter to a data window, each filter comprising a set of weights for combination with respective data values of a data window, and each of the plurality of convolution engines comprising: multiplication logic operable to combine a weight of a filter with a respective data value of a data window; control logic configured to cause the multiplication logic to combine a weight with a respective data value if the weight is non-zero, and otherwise not cause the multiplication logic to combine that weight with that data value; and accumulation logic configured to accumulate the results of a plurality of combinations performed by the multiplication logic so as to form an output for a respective convolution operation.
Source: USPTO / EPO open patent data. Objective bibliographic and citation counts.