In this paper, we propose a variable metric method for unconstrained multiobjective optimization problems (MOPs). First, sequence of points is generated using different positive definite matrices in the generic framework. It proved that accumulation are Pareto critical points. Then, without convexity assumption, strong convergence established proposed method. Moreover, use common matrix to appr...

The paper presents an overview of global issues in optimization methods for Supervised Learning (SL). We focus on Feedforward Neural Networks with the aim of reviewing global methods specifically devised for the class of continuous unconstrained optimization problems arising both in Multi Layer Perceptron/Deep Networks and in Radial Basis Networks. We first recall the learning optimization para...