Patent · US Active

Weight initialization for machine learning models

US10395141B2 · kind B2 · utility

4Cited by
4References
18Claims
0Family size

Assignee

Inventors

Key dates

Filing dateMar 20, 2017
Grant dateAug 27, 2019
Priority date
Expiry dateSep 19, 2037

Classification

  • Technology area (CPC G)Physics
  • CPC primaryG06T2210/22
  • WIPO fieldComputer technology
  • WIPO sectorElectrical engineering

Abstract

In one respect, there is provided a system that may include a processor and a memory. The memory may be configured to store instructions that results in operations when executed by the processor. The operations may include: processing an image set with a convolutional neural network configured to detect, in the image set, a first feature and a second feature; determining a respective effectiveness of the first feature and the second feature in enabling the convolutional neural network to classify images in the image set; determining, based at least on the respective effectiveness of the first feature and the second feature, a first initial weight for the first feature and a second initial weight for the second feature; and initializing the convolutional neural network for training, the initialization of the convolutional neural network comprising configuring the convolutional neural network to apply the first initial weight and the second initial weight.

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