In this study the three dimensional vibration analysis of an adhesively bonded cantilevered composite single lap joint was carried out. The first four bending natural frequencies and mode shapes were considered. The back-propagation Artificial Neural Network (ANN) method was used to determine the effects of the fiber angle, fiber volume fraction, overlap length and plate thickness on the bending natural frequencies and the mode shapes of the adhesive joint. The bending natural frequencies and modal strain energies of the composite adhesive lap joint were calculated using the finite element method for random values of the fiber angle, the fiber volume fraction, the overlap length and the plate thickness. Later, the proposed neural network models were trained and tested with the training and testing data. The fiber angle was more dominant parameter than the fiber volume fraction on the natural bending frequencies and corresponding bending mode shapes, and the plate thickness and the overlap length were also important geometrical design parameters whereas the adhesive thickness had a minor effect. In addition, the present ANN models were combined with Genetic Algorithm to search a joint design satisfying maximum natural frequency and minimum modal strain energy conditions for each natural bending frequency and mode shape.