Computationally efficient softmax loss gradient backpropagation
US11836629B2 · kind B2 · utility
Assignee
Inventor
Key dates
| Filing date | Jan 15, 2020 |
| Grant date | Dec 5, 2023 |
| Priority date | — |
| Expiry date | Sep 17, 2042 |
Classification
- Technology area (CPC G)Physics
- CPC primaryG06N3/045
- WIPO fieldComputer technology
- WIPO sectorElectrical engineering
Abstract
A computation unit comprises first, second, and third circuits. The first circuit traverses gradient loss elements gpn and normalized output elements pn and produces an accumulation C. The accumulation C is produced by element-wise multiplying the gradient loss elements gpn with the corresponding normalized output elements pn and summing the results of the element-wise multiplication. The second circuit, operatively coupled to the first circuit, element-wise subtracts the accumulation C from each of the gradient loss elements gpn and produces modulated gradient loss elements gpn′. The third circuit, operatively coupled to the second circuit, traverses the modulated gradient loss elements gpn′ and produces gradient loss elements gxn for a function preceding the softmax function. The gradient loss elements gxn are produced by element-wise multiplying the modulated gradient loss elements gpn′ with the corresponding normalized output elements pn.
Source: USPTO / EPO open patent data. Objective bibliographic and citation counts.