Login / Signup

Stochastic approximation with averaging and feedback: rapidly convergent "on-line" algorithms.

Harold J. KushnerJichuan Yang
Published in: IEEE Trans. Autom. Control. (1995)
Keyphrases
  • stochastic approximation
  • learning algorithm
  • monte carlo
  • neural network
  • computational complexity
  • policy iteration
  • data mining
  • decision trees
  • artificial neural networks