Rutherford backscattering (RBS) is a nondestructive, fully quantitative technique for accurately determining the compositional depth profile of thin films. The inverse RBS problem, which is to determine from the data the corresponding sample structure, is, however, in general ill posed. Skilled analysts use their knowledge and experience to recognize recurring features in the data and relate them to features in the sample structure. This is then followed by a detailed quantitative analysis. We have developed an artificial neural network (ANN) for the same purpose, applied to the specific case of Ge-implanted Si. The ANN was trained with thousands of constructed spectra of samples for which the structure is known. It thus learns how to interpret the spectrum of a given sample, without any knowledge of the physics involved. The ANN was then applied to experimental data from samples of unknown structure. The quantitative results obtained were compared with those given by traditional analysis methods and are excellent. The major advantage of ANNs over those other methods is that, after the time-consuming training phase, the analysis is instantaneous, which opens the door to automated on-line data analysis. Furthermore, the ANN was able to distinguish two different classes of data which are experimentally difficult to analyze. This opens the door to automated on-line optimization of the experimental conditions.