Research output: Contribution to journal › Article › peer-review
A randomized stochastic approximation algorithm for self-learning. / Granichin, ON; Izmakova, OA.
In: Automation and Remote Control, Vol. 66, No. 8, 2005, p. 1239-1248.Research output: Contribution to journal › Article › peer-review
}
TY - JOUR
T1 - A randomized stochastic approximation algorithm for self-learning
AU - Granichin, ON
AU - Izmakova, OA
PY - 2005
Y1 - 2005
N2 - A new stochastic approximation algorithm with input perturbation for self-learning is designed with test perturbations and has certain useful properties, such as consistency of estimates tinder almost arbitrary perturbations and preservation of simplicity and performance with the growing size of the state space and increasing number of classes. An example. oil computer-aided modeling of learning is given to illustrate the performance of the algorithm.
AB - A new stochastic approximation algorithm with input perturbation for self-learning is designed with test perturbations and has certain useful properties, such as consistency of estimates tinder almost arbitrary perturbations and preservation of simplicity and performance with the growing size of the state space and increasing number of classes. An example. oil computer-aided modeling of learning is given to illustrate the performance of the algorithm.
U2 - 10.1007/s10513-005-0165-3
DO - 10.1007/s10513-005-0165-3
M3 - статья
VL - 66
SP - 1239
EP - 1248
JO - Automation and Remote Control
JF - Automation and Remote Control
SN - 0005-1179
IS - 8
ER -
ID: 5014772