Artificial Neural Networks ANNs

Artificial Neural Networks. An Artificial Neural Network (ANN) consists of a network of nodes (processing elements) connected via adjustable weights [Zurada, 1992]. The weights can be adjusted so that a network learns a mapping represented by a set of example input/output pairs. An ANN can in theory reproduce any continuous function 95 —>31 °, where n and m are numbers of input and output nodes. In NDT neural networks are usually used as classifiers... 

Kohonen networks, also known as self-organizing maps (SOMs), belong to the large group of methods called artificial neural networks. Artificial neural networks (ANNs) are techniques which process information in a way that is motivated by the functionality of biological nervous systems. For a more detailed description see Section 9.5. 

Artificial Neural Networks (ANNs) are information processing imits which process information in a way that is motivated by the functionality of the biological nervous system. Just as the brain consists of neurons which are connected with one another, an ANN comprises interrelated artificial neurons. The neurons work together to solve a given problem. 

Artificial Neural Networks (ANNs) attempt to emulate their biological counterparts. McCulloch and Pitts (1943) proposed a simple model of a neuron, and Hebb (1949) described a technique which became known as Hebbian learning. Rosenblatt (1961), devised a single layer of neurons, called a Perceptron, that was used for optical pattern recognition. 

Recently, a new approach called artificial neural networks (ANNs) is assisting engineers and scientists in their assessment of fuzzy information, Polymer scientists often face a situation where the rules governing the particular system are unknown or difficult to use. It also frequently becomes an arduous task to develop functional forms/empirical equations to describe a phenomena. Most of these complexities can be overcome with an ANN approach because of its ability to build an internal model based solely on the exposure in a training environment. Fault tolerance of ANNs has been found to be very advantageous in physical property predictions of polymers. This chapter presents a few such cases where the authors have successfully implemented an ANN-based approach for purpose of empirical modeling. These are not exhaustive by any means. 

Intelligent structures are smart structures that have the added capability of learning and adapting rather than simply responding in a programmed manner, and this is usually accomplished by inclusion of Artificial Neural Network (ANN) into the stmcture (Figure 10.2). 

Bourquin J, Schmidli H, van Hoogevest P, Leuenberger H. Basic concepts of artificial neural networks (ANN) modelling in the application to pharmaceutical development. Pharm Dev Technol 1997 2 95-109. 

Aqueous solubility is selected to demonstrate the E-state application in QSPR studies. Huuskonen et al. modeled the aqueous solubihty of 734 diverse organic compounds with multiple linear regression (MLR) and artificial neural network (ANN) approaches [27]. The set of structural descriptors comprised 31 E-state atomic indices, and three indicator variables for pyridine, ahphatic hydrocarbons and aromatic hydrocarbons, respectively. The dataset of734 chemicals was divided into a training set ( =675), a vahdation set (n=38) and a test set (n=21). A comparison of the MLR results (training, r =0.94, s=0.58 vahdation r =0.84, s=0.67 test, r =0.80, s=0.87) and the ANN results (training, r =0.96, s=0.51 vahdation r =0.85, s=0.62 tesL r =0.84, s=0.75) indicates a smah improvement for the neural network model with five hidden neurons. These QSPR models may be used for a fast and rehable computahon of the aqueous solubihty for diverse orgarhc compounds. 

In Chapter 43 the incorporation of expertise and experience in data analysis by means of expert systems is described. The knowledge acquisition bottleneck and the brittleness of domain expertise are, however, the major drawbacks in the development of expert systems. This has stimulated research on alternative techniques. Artificial neural networks (ANN) were first developed as a model of the human brain structure. The computerized version turned out to be suitable for performing tasks that are considered to be difficult to solve by classical techniques. 

In analytical chemistry, Artificial Neural Networks (ANN) are mostly used for calibration, see Sect. 6.5, and classification problems. On the other hand, feedback networks are usefully to apply for optimization problems, especially nets ofHoPFiELD type (Hopfield [1982] Lee and Sheu [1990]). 

Another form of artificial intelligence is realized in artificial neural networks (ANN). The principle of ANNs has been presented in Sect. 6.5. Apart from calibration, data analysis and interpretation is one of the most important fields of application of ANNs in analytical chemistry (Tusar et al. [1991] Zupan and Gasteiger [1993]) where two branches claim particular interest ... 

The brain s remarkable ability to learn through a process of pattern recognition suggests that, if we wish to develop a software tool to detect patterns in scientific or, indeed, any other kind of data, the structure of the brain could be a productive starting point. This view led to the development of artificial neural networks (ANNs). The several methods that are gathered under the ANN umbrella constitute some of the most widely used applications of Artificial Intelligence in science. Typical areas in which ANNs are of value include ... 

Since in many applications minor absorption changes have to be detected against strong, interfering background absorptions of the matrix, advanced chemometric data treatment, involving techniques such as wavelet analysis, principle component analysis (PCA), partial least square (PLS) methods and artificial neural networks (ANN), is a prerequisite. 

In an early application of in silico approaches to predict human VD, Ritschel and coworkers described an approach using artificial neural networks (ANN), in this case for VDp [34]. However, this was not a truly in silico-only approach as the ANN that yielded accurate predictions of human VD required animal pharmacokinetic data as input parameters, along with in vitro data (protein binding and logP). 

Compared with the artificial neural network (ANN) approach used in previous work to predict CN12 the linear regression model by QSAR is as good or better and easier to implement. The predicted CN values, some of which are tabulated in Table 1, will be employed below to evaluate the different catalytic strategies to optimize the fuel. 

Models of the form y =f(x) or v =/(x1, x2,..., xm) can be linear or nonlinear they can be formulated as a relatively simple equation or can be implemented as a less evident algorithmic structure, for instance in artificial neural networks (ANN), tree-based methods (CART), local estimations of y by radial basis functions (RBF), k-NN like methods, or splines. This book focuses on linear models of the form... 

Degim T, Hadgraft J, Ilbasmis S, Ozkan Y (2003) Prediction of skin penetration using artificial neural network (ANN) modeling. J Pharm Sci 92 656-664. 

Yamamura S (2003) Clinical application of artificial neural network (ANN) modeling to predict pharmacokinetic parameters of severely ill patients. Adv Drug Deliv Rev 5 1233-1251. 

McGovern et al.26 analyzed the expression of heterologous proteins in E. coli via pyrolysis mass spectrometry and FT-IR. The application was to a2-interferon production. To analyze the data, artificial neural networks (ANN) and PLS were utilized. Because cell pastes contain more mass than the supernatant, these were used for quantitative analyses. Both the MS and IR data were difficult to interpret, but the chemometrics used allowed researchers to gain some knowledge of the process. The authors show graphics indicating the ability to follow production via either technique. 

---