Patent · US Active

Structure learning in convolutional neural networks

US11657286B2 · kind B2 · utility

0Cited by
51References
19Claims
0Family size

Assignee

Inventors

Key dates

Filing dateFeb 23, 2021
Grant dateMay 23, 2023
Priority date
Expiry dateFeb 23, 2041

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.