We introduce a hybrid neural-genetic multimodel parameter estimation a
lgorithm. The algorithm is applied to structured system identification
of nonlinear dynamical systems. The main components of the algorithm
are 1) a recurrent incremental credit assignment (ICRA) neural network
, which computes a credit function for each member of a generation of
models and 2) a genetic algorithm which uses the credit functions as s
election probabilities for producing new generations of models. The ne
ural network and genetic algorithm combination is applied to the task
of finding the parameter values which minimize the total square output
error: the credit function reflects the closeness of each model's out
put to the true system output and the genetic algorithm searches the p
arameter space by a divide-and-conquer technique. The algorithm is eva
luated by numerical simulations of parameter estimation for a planar r
obotic manipulator and a waste water treatment plant.