Ricerc@Sapienza

The paper presents an overview of global issues in optimizationmethods for training feedforward
neural networks (FNN) in a regression setting.We first recall the learning optimization
paradigm for FNN and we briefly discuss global scheme for the joint choice of the network
topologies and of the network parameters. The main part of the paper focuses on the
core subproblem which is the continuous unconstrained (regularized) weights optimization
problem with the aim of reviewing global methods specifically arising both in multi layer

Granular Computing is a powerful information processing paradigm for synthesizing advanced pattern recognition systems in non-conventional domains. In this paper, a novel procedure for the automatic synthesis of suitable information granules is proposed. The procedure leverages a joint sensitivity-vs-specificity score that accounts the meaningfulness of candidate information granules for each class considered in the classification problem at hand.

The role performed by a protein is directly connected to its physico-chemical structure. How the latter affects the behaviour of these molecules is still an open research topic. In this paper we consider a subset of the Escherichia Coli proteome where each protein is represented through the spectral characteristics of its residue contact network and its physiological function is encoded by a suitable class label. By casting this problem as a machine learning task, we aim at assessing whether a relation exists between such spectral properties and the protein’s function.