A new formulation of the learning problem for a neural network controller

In this paper we consider the learning problem for a class of multilayer perceptrons which is practically relevant in control systems applications. By reformulating this problem, a new criterion is developed, which reduces the number of iterations required for the learning phase.

Constitutive OGG1 variant together with BRCA mutations display accelerated telomere shortening

Dissertação de mestrado, Oncobiologia, Departamento de Ciências Biomédicas e Medicina, Universidade do Algarve, 2015