Neural networks applied in chemistry. I. Determination of the optimal topology of multilayer perceptron neural networks

Abstract

Artificial neural networks (ANNs) are comparatively straightforward to understand and use in the analysis of scientific data. However, this relative transparency may encourage their use in an uncritical, and therefore possibly unproductive, fashion. The geometry of a network is among the most crucial factors in the successful deployment of network tools; in this review, we cover methods that can be used to determine optimum or near-optimum geometries. These methods of determining neural network architecture include the following: (i) trial and error, in which architectures chosen semirandomly are tested and modified by the user; (ii) empirical or statistical methods, in which an ANN's internal parameters are adjusted based on the model's performance; (iii) hybrid methods, such as fuzzy inference; (iv) constructive and/or pruning algorithms, that add and/or remove neurons or weights from an initial architecture, respectively, based on a predefined link between architecture and ANN performance; (v) evolutionary strategies, which search the topology space using genetic operators to vary the neural network parameters. Several case studies illustrate the development of neural network models for applications in chemistry and chemical engineering.

Spectroscopic determination of the photodegradation of monovarietal extra virgin olive oils and their binary mixtures through intelligent systems

“…3). The quantity of neurons that occupy the output layer depends on the number of dependent variables considered in the system modeled, while the number of units in the hidden layer requires further optimization (vide infra) [21]. On the other hand, as the input nodes present the value of the independent variables to the model, there must be as many nodes as independent variables.…”

“…These algorithms are able to determine non-linear relations between dependent and independent variables within databases through non-linear interpolation. Even though there are different kinds of ANNs, the supervised multilayer perceptron (MLP) is one of the most successfully employed ANNs in scientific research [20,21], and it was the one selected to assist in the case proposed. As it is a supervised-learning ANN, there must be both input and target data so the MLP can be correctly trained and optimized [22].…”

Estimation of Chlamydomonas reinhardtii biomass concentration from chord length distribution data

“…The authors chose to model the relationship between CLD data and dry biomass using artificial neural networks (ANN), in particular feedforward multilayer perceptrons, given their proven efficacy in solving problems related to sensing and spectra interpretation in the fields of Biotechnology (Strapasson et al 2014) and Chemical Engineering (Curteanu and Cartwright 2011; Pirdashti et al 2013; Ali et al 2015). ANN have been employed occasionally to estimate biomass concentration of yeasts in fermentation (e.g.…”

Breakdown potential modelling of austenitic stainless steel

“…The principal objective was to obtain a reliable tool with the ability to predict the breakdown potential for the range of the environmental conditions considered in the study automatically, without the need to require polarization tests. On the other hand, although ANNs have been demonstrated to be a suitable tool to solve many engineering problems [25], they can suffer from some drawbacks such as the no existence of method to define the structure, the sensitivity of the training process to the initial weights or the overtraining [26]. Parthiban et al [22] used artificial neural networks (ANNs) to estimate potential values of embedded steel, whereas Boucherit et al [23] tried to predict localized corrosion of the carbon steel.…”