Patent · US Active

System and method for distributive training and weight distribution in a neural network

US10217028B1 · kind B1 · utility

24Cited by
1References
20Claims
0Family size

Assignee

Inventors

Key dates

Filing dateAug 22, 2017
Grant dateFeb 26, 2019
Priority date
Expiry dateSep 28, 2037

Classification

  • Technology area (CPC G)Physics
  • CPC primaryG06T2207/20084
  • WIPO fieldComputer technology
  • WIPO sectorElectrical engineering

Abstract

A system for distributive training and weight distribution in a neural network. The system includes a training facility having a training neural network that detects and classifies objects in training images so as to train weights of nodes in the training neural network, and a plurality of object detection and classification units each including an image source that provides image frames, and at least one classification and prediction neural network that identifies, classifies and indicates relative velocity of objects in the image frames. Each unit transmits its image frames to the training facility so that the training neural network further trains the weights of the nodes in the training neural network, and the trained neural network weights are transmitted from the training facility to each of the object detection and classification units so as to train weights of nodes in the at least one classification and prediction neural network.

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