The performance of machine learning algorithms is conditioned by the availability of training datasets, which is especially true for the field of nondestructive evaluation. Here we propose one reconfigurable specimen instead of numerous reference specimens with known, unchangeable defect properties, which are usually complicated to fabricate. It consist of a shape memory polymer foil with temperature-dependent Young’s modulus and ultrasound attenuation. This open a possibility to generate a reconfigurable defect by projecting a heating laser in the form of a short line on the specimen surface. Ultrasound is generated by a laser pulse at one fixed position and detected by a laser vibrometer at another fixed position for 64 different defect positions and 3 different configurations of the specimen. The obtained diversified datasets are used to optimize the neural network architecture for the interpretation of ultrasound signals. We study the performance of the model in cases of reduced and dissimilar training datasets. In our first study, we classify the specimen configurations with the defect position being the disturbing parameter. The model shows high performance on a dataset of signals obtained at all the defect positions, even if trained on a completely different dataset containing signals obtained at only few defect positions. In our second study, we perform precise defect localization. The model becomes robust to the changes in the specimen configuration when a reduced dataset, containing signals obtained at two different specimen configurations, is used for the training process. This work highlights the potential of the demonstrated machine learning algorithm for industrial quality control. High-volume products (simulated by a reconfigurable specimen in our work) can be rapidly tested on the production line using this single-point and contact-free laser ultrasonic method.