Structure learning in convolutional neural networks
US10255529B2 · kind B2 · utility
11Cited by
45References
33Claims
0Family size
Assignee
Inventors
Key dates
| Filing date | Mar 13, 2017 |
| Grant date | Apr 9, 2019 |
| Priority date | — |
| Expiry date | Mar 13, 2037 |
Classification
- Technology area (CPC G)Physics
- CPC primaryG06V30/194
- WIPO fieldComputer technology
- WIPO sectorElectrical engineering
Abstract
The present disclosure provides an improved approach to implement structure learning of neural networks by exploiting correlations in the data/problem the networks aim to solve. A greedy approach is described that finds bottlenecks of information gain from the bottom convolutional layers all the way to the fully connected layers. Rather than simply making the architecture deeper, additional computation and capacitance is only added where it is required.
Source: USPTO / EPO open patent data. Objective bibliographic and citation counts.