Highly trainable neural network configuration
US10984320B2 · kind B2 · utility
0Cited by
13References
28Claims
0Family size
Assignee
Inventors
Key dates
| Filing date | May 1, 2017 |
| Grant date | Apr 20, 2021 |
| Priority date | — |
| Expiry date | Jan 20, 2040 |
Classification
- Technology area (CPC G)Physics
- CPC primaryG06N3/048
- WIPO fieldComputer technology
- WIPO sectorElectrical engineering
Abstract
A computer-based method includes receiving an input signal at a neuron in a computer-based neural network that includes a plurality of neuron layers, applying a first non-linear transform to the input signal at the neuron to produce a plain signal, and calculating a weighted sum of a first component of the input signal and the plain signal at the neuron. In a typical implementation, the first non-linear transform is a function of the first component of the input signal and at least a second component of the input signal.
Source: USPTO / EPO open patent data. Objective bibliographic and citation counts.