Patent · US Active

Loss-aware replication of neural network layers

US11847567B1 · kind B1 · utility

3Cited by
6References
21Claims
0Family size

Assignee

Inventors

Key dates

Filing dateJul 7, 2020
Grant dateDec 19, 2023
Priority date
Expiry dateJul 28, 2042

Classification

  • Technology area (CPC G)Physics
  • CPC primaryG06N20/00
  • WIPO fieldComputer technology
  • WIPO sectorElectrical engineering

Abstract

Some embodiments provide a method that receives a network with trained floating-point weight values. The network includes layers of nodes, each of which computes an output value based on input values and trained weight values. To replace a first layer of the trained network in a modified network with quantized weight values, the method defines multiple replica layers. Each replica layer includes nodes that correspond to nodes of the first layer, has a different set of allowed quantized weight values, and receives the same input values from a previous layer of the modified network such that groups of corresponding nodes from the replica layers operate correspondingly to the first layer. The method trains the quantized weight values of the modified network using a loss function with terms that account for effect on the loss function due to the quantization and for interactions between corresponding weight values of the replica layers.

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