Patent · US Expired

Self-organizing feature map with improved performance by non-monotonic variation of the learning rate

US6965885B2 · kind B2 · utility

4Cited by
9References
14Claims
0Family size

Assignee

Inventors

Key dates

Filing dateJan 22, 2002
Grant dateNov 15, 2005
Priority date
Expiry dateFeb 17, 2023

Classification

  • Technology area (CPC G)Physics
  • CPC primaryG06N3/0895
  • WIPO fieldComputer technology
  • WIPO sectorElectrical engineering

Abstract

The learning rate used for updating the weights of a self-ordering feature map is determined by a process that injects some type of perturbation into the value so that it is not simply monotonically decreased with each training epoch. For example, the learning rate may be generated according to a pseudorandom process. The result is faster convergence of the synaptic weights.

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