We have utilized neural networks for fast evaluation of tomographic da
ta on the MT-1M tokamak. The networks have proven useful in providing
the parameters of a nonlinear fit to experimental data, producing resu
lts in a fraction of the time required for performing the nonlinear fi
t. Time required for training the networks makes the method worth appl
ying only if a substantial amount of data are to be evaluated. (C) 199
7 American Institute of Physics.