Patent · US Active

Systems and methods for quantizing neural networks via periodic regularization functions

US11468313B1 · kind B1 · utility

11Cited by
0References
20Claims
0Family size

Assignee

Inventors

Key dates

Filing dateJun 12, 2018
Grant dateOct 11, 2022
Priority date
Expiry dateAug 12, 2041

Classification

  • Technology area (CPC G)Physics
  • CPC primaryG06N3/063
  • WIPO fieldComputer technology
  • WIPO sectorElectrical engineering

Abstract

The disclosed computer-implemented method may include (1) identifying an artificial neural network comprising a set of nodes interconnected via a set of connections, and (2) training the artificial neural network by, for each connection in the set of connections, determining a quantized weight value associated with the connection. Determining the quantized weight value associated with the connection may include (1) associating a loss function with the connection, the loss function including a periodic regularization function that describes a relationship between an input value and a weight value of the connection, (2) determining a minimum of the associated loss function with respect to the weight value in accordance with the periodic regularization function, and (3) generating the quantized weight value associated with the connection based on the determined minimum of the loss function. Various other methods, systems, and computer-readable media are also disclosed.

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