Patent · US Active

Systems and methods for training neural networks based on concurrent use of current and recorded data

US8489528B2 · kind B2 · utility

2Cited by
5References
19Claims
0Family size

Assignee

Inventors

Key dates

Filing dateJul 28, 2010
Grant dateJul 16, 2013
Priority date
Expiry dateMay 31, 2031

Classification

  • Technology area (CPC G)Physics
  • CPC primaryG06N3/09
  • WIPO fieldComputer technology
  • WIPO sectorElectrical engineering

Abstract

Various embodiments of the invention are neural network adaptive control systems and methods configured to concurrently consider both recorded and current data, so that persistent excitation is not required. A neural network adaptive control system of the present invention can specifically select and record data that has as many linearly independent elements as the dimension of the basis of the uncertainty. Using this recorded data along with current data, the neural network adaptive control system can guarantee global exponential parameter convergence in adaptive parameter estimation problems. Other embodiments of the neural network adaptive control system are also disclosed.

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