Patent · US Active

Structure learning in convolutional neural networks

US10963758B2 · kind B2 · utility

1Cited by
46References
21Claims
0Family size

Assignee

Inventors

Key dates

Filing dateMar 27, 2019
Grant dateMar 30, 2021
Priority date
Expiry dateApr 12, 2039

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.