Comparative study between RBF and radial-PPS neural networks

The study of function approximation is motivated by the human limitation and inability to register and manipulate with exact precision the behavior variations of the physical nature of a phenomenon. These variations are referred to as signals or signal functions. Many real world problem can be formulated as function approximation problems and from the viewpoint of artificial neural networks these can be seen as the problem of searching for a mapping that establishes a relationship from an input space to an output space through a process of network learning. Several paradigms of artificial neural networks (ANN) exist. Here we will be investigated a comparative of the ANN study of RBF with radial Polynomial Power of Sigmoids (PPS) in function approximation problems. Radial PPS are functions generated by linear combination of powers of sigmoids functions. The main objective of this paper is to show the advantages of the use of the radial PPS functions in relationship traditional RBF, through adaptive training and ridge regression techniques.

A DOE based approach for the design of RBF artificial neural networks applied to prediction of surface roughness in AISI 52100 hardened Steel turning

Coordenação de Aperfeiçoamento de Pessoal de Nível Superior (CAPES)

Optimization of Radial Basis Function neural network employed for prediction of surface roughness in hard turning process using Taguchi's orthogonal arrays

Conselho Nacional de Desenvolvimento Científico e Tecnológico (CNPq)

Variational studies and replica symmetry breaking in the generalization problem of the binary perceptron

We analyze the average performance of a general class of learning algorithms for the nondeterministic polynomial time complete problem of rule extraction by a binary perceptron. The examples are generated by a rule implemented by a teacher network of similar architecture. A variational approach is used in trying to identify the potential energy that leads to the largest generalization in the thermodynamic limit. We restrict our search to algorithms that always satisfy the binary constraints. A replica symmetric ansatz leads to a learning algorithm which presents a phase transition in violation of an information theoretical bound. Stability analysis shows that this is due to a failure of the replica symmetric ansatz and the first step of replica symmetry breaking (RSB) is studied. The variational method does not determine a unique potential but it allows construction of a class with a unique minimum within each first order valley. Members of this class improve on the performance of Gibbs algorithm but fail to reach the Bayesian limit in the low generalization phase. They even fail to reach the performance of the best binary, an optimal clipping of the barycenter of version space. We find a trade-off between a good low performance and early onset of perfect generalization. Although the RSB may be locally stable we discuss the possibility that it fails to be the correct saddle point globally. ©2000 The American Physical Society.

Influence of the network modifier on the characteristics of MSnO 3 (M=Sr and Ca) thin films synthesized by chemical solution deposition

CaSnO3 and SrSnO3 alkaline earth stannate thin films were prepared by chemical solution deposition using the polymeric precursor method on various single crystal substrates (R- and C-sapphire and 100-SrTiO3) at different temperatures. The films were characterized by X-ray diffraction (θ-2θ, ω- and φ-scans), field emission scanning electron microscopy, atomic force microscopy, micro-Raman spectroscopy and photoluminescence. Epitaxial SrSnO3 and CaSnO 3 thin films were obtained on SrTiO3 with a high crystalline quality. The long-range symmetry promoted a short-range disorder which led to photoluminescence in the epitaxial films. In contrast, the films deposited on sapphire exhibited a random polycrystalline growth with no meaningful emission regardless of the substrate orientation. The network modifier (Ca or Sr) and the substrate (sapphire or SrTiO3) influenced the crystallization process and/or the microstructure. Higher is the tilts of the SnO6 octahedra, as in CaSnO3, higher is the crystallization temperature, which changed also the nucleation/grain growth process. © 2012 Elsevier Inc. All rights reserved.

Influence of the network modifier on the characteristics of MSnO3 (M=Sr and,Ca) thin films synthesized by chemical solution deposition

Coordenação de Aperfeiçoamento de Pessoal de Nível Superior (CAPES)