Types of Artificial Neural Network

To provide you with a solid basis for deciding whether or not a given ANN is appropriate for your intended use, we describe briefly in this section many of the types of ANNs that have appeared in the literature in the past few years. For each network we focus on strengths and weaknesses, some practical aspects of operation, and a literature review of the chemical applications. We do not delve into detailed mathematical descriptions of networks, since these can be found in any number of texts. In particular we call attention to Ref. 19, which offers step-by-step developments of equations and detailed numerical examples for backpropagation, biassociative memory, counterpropagation, Hopfield, and Kohonen self-organizing map networks. Adaptive resonance theory networks are reviewed in detail in Ref. 27. 

Most uses of ART networks by the chemical community are very recent. In applications related to infrared spectroscopy, they have been used to recognize aromatic substitution pattems (they reportedly performed better than human experts) and also in the clustering of spectra of lubricating base oils. Reference 83 also contains a good comparison of ART networks with other methods. ART networks have also been applied in choosing a detector for ion 

---

Several types of artificial neural networks have been used as pattern recognition engines. In general, neural networks are mathematical models that emulate some of the observed properties of biological nervous systems, in particular the ability to learn complex relationships. Examples of drug-like molecules were taken from the WDI, CMC or MDDR databases, while compounds from the ACD database exemplified nondrugs. Molecules were represented by a large number of descriptors, such as ISIS... 

Finally, one class of unsupervised methods is represented by self-organising maps (SOM), or Kohonen maps, named after the Finnish professor Teuvo Kohonen. A SOM is a type of artificial neural network that needs to be trained but does not require labelling of the input vectors. Examples of classification analysis by SOMs in biomedical IR and Raman spectroscopy are given in references. ... 

Self-Organizing Maps (SOMs) or Kohonen maps are types of Artificial Neural Networks (ANNs) that are trained using supervised/unsupervised learning to produce a low-dimensional discretized representation (typically 2-dimensional) of an arbitrary dimension of input space of the training samples (Zhong et al. 2005). 

Although the partition of the set of neurons into input, hidden and output neurons still allows a wide variety of architectures, the architecture of nearly all types of artificial neural networks more frequently encountered in practical applications is essentially the same, namely a layered architecture. This type of architecture is characterised by the following properties ... 

The constants a, b, and c define the sigmoid curve, which has the asymptotic values zero for x —> —X and a for x 4-Y (a and c are expected to have positive values). The position and steepness of the curve between the two asymptotic values depend on the parameters b and c. A logistic function is the result of a logistic regression analysis, where b + cx is replaced by a linear combination of all x-variables. With values 1, 0, and 1 for a, b, and c, respectively, the logistic function is often used as a transfer function for back-propagation networks, a type of artificial neural network. See Neural Networks in Chemistry. 

There are many types of artificial neural networks, and they are used for different applications. The type of network used affects both the quality and speed of the learning process. They can be categorized by structure as follows ... 

By design, ANNs are inherently flexible (can map nonlinear relationships). They produce models well suited for classification of diverse bacteria. Examples of pattern analysis using ANNs for biochemical analysis by PyMS can be traced back to the early 1990s.4fM7 In order to better demonstrate the power of neural network analysis for pathogen ID, a brief background of artificial neural network principles is provided. In particular, backpropagation artificial neural network (backprop ANN) principles are discussed, since that is the most commonly used type of ANN. 

The field of artificial neural networks is a new and rapidly growing field and, as such, is susceptible to problems with naming conventions. In this book, a perceptron is defined as a two-layer network of simple artificial neurons of the type described in Chapter 2. The term perceptron is sometimes used in the literature to refer to the artificial neurons themselves. Perceptrons have been around for decades (McCulloch Pitts, 1943) and were the basis of much theoretical and practical work, especially in the 1960s. Rosenblatt coined the term perceptron (Rosenblatt, 1958). Unfortunately little work was done with perceptrons for quite some time after it was realized that they could be used for only a restricted range of linearly separable problems (Minsky Papert, 1969). 

Neural network has been widely used in fields of function approximation, pattern recognition, image dealing, artificial intelligence, optimization and so on [26, 102]. Multilayer feed forward artificial neural network is a major type of the neural network which is connected by input layer, one or more output layers and hidden layers in a forward way. Each layer is composed of many artificial neurons. The output of previous layer neurons is the input of the next layer as shown in Fig. 2.6. 

The main reason for the utility of artificial neural networks (ANN) for modeling purposes is related to the incomplete knowledge of the mechanisms of polymerization processes and to the fact that the available phenomenological models are being developed and solved with difficulty or do not provide accurate results. For these types of processes, designing neural networks represents modeling alternatives for providing predictions useful for experimental practice. 

This chapter serves as a short introduction to the field of artificial neural networks, or simply neural networks. Its aim is to provide readers with a basic understanding of these systems. Two main types of neural networks are dealt with traditional neural networks and dynamic neural networks. 

A basic information about Artificial Neural Networks (ANNs) and their applications was introduced. A special attention was given to description of dynamic processes by mean of ANN. The drying kinetics of agricultural products are presented in the paper. Multilayer Perceptron (MLP) and Radial Basis Function (RBF) network types are proposed for predicting changes of moisture content and temperature of material in during drying in the vibrofluidized bed. Capability of prediction of Artificial Neural Networks is evaluated in feed forward and recurrent structures. 

The exceptional computational abilities of the human brain have motivated the concept of an NN. The brain can perform certain types of computation, such as perception, pattern recognition, and motor control, much faster than existing digital computers (Haykin, 2009). The operation of the human brain is complex and nonlinear and involves massive parallel computation. Its computations are performed using structural constituents called neurons and the synaptic interconnections between them (that is, a neural network), The development of artificial neural networks is an admittedly approximate attempt to mimic this biological neural network, in order to achieve some of its computational advantages. 

There are many possibilities to connect artificial neurons into a network and to direct the flow of signals in the network. For this reason, we can distinguish many kinds of artificial neural networks, each of which has its own method for selecting the weights (learning). The most basic types of neural networks are ... 

---