Patent · US Active

Neural network compression device and method for same

US12142030B2 · kind B2 · utility

0Cited by
1References
15Claims
0Family size

Assignee

Inventor

Key dates

Filing dateOct 30, 2020
Grant dateNov 12, 2024
Priority date
Expiry dateOct 21, 2041

Classification

  • Technology area (CPC G)Physics
  • CPC primaryG06V20/56
  • WIPO fieldComputer technology
  • WIPO sectorElectrical engineering

Abstract

When it is assumed that a large-scale Deep Neural Network for autonomous driving applied compression, there are problems of a decrease in recognition accuracy of a post-compression Neural Network (NN) model and an increase in a compression design period, due to a large number of harmful or unnecessary training images (invalid training images). A training image selection unit B100 calculates an influence value on an inference, and generates an indexed training image set 1004-1 necessary for an NN compression design, by using the influence value. A neural network compression unit P200 notified of the result via a memory P300 compresses the NN.

Source: USPTO / EPO open patent data. Objective bibliographic and citation counts.