Patent · US Active

Replication of neural network layers

US11604973B1 · kind B1 · utility

3Cited by
18References
20Claims
0Family size

Assignee

Inventors

Key dates

Filing dateNov 27, 2019
Grant dateMar 14, 2023
Priority date
Expiry dateJun 2, 2041

Classification

  • Technology area (CPC G)Physics
  • CPC primaryG06N3/0495
  • WIPO fieldComputer technology
  • WIPO sectorElectrical engineering

Abstract

Some embodiments provide a method for training parameters of a machine-trained (MT) network. The method receives an MT network with multiple layers of nodes, each of which computes an output value based on a set of input values and a set of trained weight values. Each layer has a set of allowed weight values. For a first layer with a first set of allowed weight values, the method defines a second layer with nodes corresponding to each of the nodes of the first layer, each second-layer node receiving the same input values as the corresponding first-layer node. The second layer has a second, different set of allowed weight values, with the output values of the nodes of the first layer added with the output values of the corresponding nodes of the second layer to compute output values that are passed to a subsequent layer. The method trains the weight values.

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