Evolving Systems manuscript No. (will be inserted by the editor) On ensemble techniques of weight-constrained neural networks Ioannis E. Livieris · Lazaros Iliadis · Panagiotis Pintelas Abstract Ensemble learning constitutes one of the most fundamental and reliable strategies for building powerful and accurate predictive models, aiming to exploit the predictions of a number of multiple learners. In this paper, we propose two ensemble prediction models which exploit the classification performance of Weight-Constrained Neural Networks (WC- NNs). The proposed models are based on Bagging and Boosting, which constitute two of the most popular strategies, to efficiently combine the predictions of WCNN classifiers. We conducted a series of experiments using a variety of benchmarks from UCI repository in order to evaluate the performance of the two proposed models against other state-of-the-art ensemble classifiers. The reported experimental results illustrate the prediction accuracy of the proposed models providing empirical evidence that the hybridization of ensemble learn- ing and WCNNs can build efficient and powerful classification models. Keywords Weight-constrained neural networks · ensemble learning · bagging · boosting- AdaBoost. I.E. Livieris Department of Mathematics, University of Patras, GR 265-00, Greece. E-mail: livieris@upatras.gr L. Iliadis Department of Civil Engineering, Democritus University of Thrace, GR 67100, Greece. E-mail: lil- iadis@civil.duth.gr P. Pintelas Department of Mathematics, University of Patras, GR 265-00, Greece. E-mail: pintelas@upatras.gr