Ferrari-Trecate, G.Muselli, M.Liberati, D.Morari, M.2017-01-102017-01-102017-01-10200110.1007/978-1-4471-0219-9_9https://infoscience.epfl.ch/handle/20.500.14299/132692A new learning algorithm for solving piecewise linear regression problems is proposed. It is able to train a proper multilayer feedforward neural network so as to reconstruct a target function assuming a different linear behavior on each set of a polyhedral partition of the input domain. The proposed method combine local estimation, clustering in weight space, classification and regression in order to achieve the desired result. A simulation on a benchmark problem shows the good properties of this new learning algorithm.text::conference output::conference proceedings::conference paper