We show, in agreement with previous studies, that neural nets can be useful for top-quark analysis at the Fermilab Tevatron. The main features of tt¯ and background events in a mixed sample are projected on a single output, which controls the efficiency, purity, and statistical significance of the tt¯ signal. We consider a feed-forward multilayer neural net for the CDF reported top-quark mass, using six kinematical variables as inputs. Our main results are based on the exhaustive comparison of the neural net performances with those obtainable from the standard experimental analysis, by imposing different sets of linear cuts over the same variables, showing how the neural net approach improves the standard analysis results.