Limitations of sensitivity analysis for neural networks in cases with dependent inputs

In this paper the limitations of the sensitivity analysis method for feedforward neural networks in the cases of dependent input variables are discussed. First, it is explained that in such cases there can be many functions implemented by neural networks that will accurately approximate training patterns. Then it is pointed out that many of these functions do not allow for proper estimation of the inputs importance using the sensitivity analysis method for neural networks. These two facts are demonstrated to be the reason why one can not completely rely upon the results of this method, when evaluating a real importance of inputs. Examples with graphs visualizing the discussed phenomena are presented. Finally, general conclusions about overall usefulness of the method are introduced.