Neural networks overview

Jansson, P. A. Anal. Chem. 63, 1991, 357-362. Neural networks An overview. 

P. A. Jansson, Neural networks an overview, Anal. Chem., 63(6), 1991, 357A-362A. 

Three commonly used ANN methods for classification are the perceptron network, the probabilistic neural network, and the learning vector quantization (LVQ) networks. Details on these methods can be found in several references.57,58 Only an overview of them will be presented here. In all cases, one can use all available X-variables, a selected subset of X-variables, or a set of compressed variables (e.g. PCs from PCA) as inputs to the network. Like quantitative neural networks, the network parameters are estimated by applying a learning rule to a series of samples of known class, the details of which will not be discussed here. 

For a detailed treatment of artificial neural networks, readers are again referred to specific monographs [35, 49-51], for a survey of their applications in chemistry to overview books [52, 53], reviews [54—56], and relevant sections of publications [57-59]. For heterogeneous catalysis, a recent overview has explained the applicability of feedforward networks to the approximation of unknown dependencies and to the extraction of logical rules from experimental data [22]. 

Spectra are very complex, and the instruments show a drift over longer times [61]. Both problems can be accounted for by data evaluation, but require sophisticated mathematical methods like supervised learning of neural networks. For a comprehensive overview and more detail, see the chapter by Shaw and Kell, this volume. 

This part of the book consists of one chapter (Chapter 1) to provide an overview of the domain field, genome informatics, with its major research areas and technologies a brief summary of the computational technology, artificial neural networks , and a summary of genome informatics applications. The latter two topics are further expanded into Part II, Neural Network Foundations, and Part III, Genome Informatics Applications. 

SIMCA and related methods Back propagation neural networks Decision trees Genetic algorithms Pattern recognition in data sets A Overview... 

In designing a neural network control system, one must select the overall structure of the system and decide which components will utilize neural network algorithms. Several examples of control system structures are provided below, each of which utilizes one or more neural networks as described above. This section of the chapter provides a brief overview of some neural control systems that have potential for application in biomedical control systems. For excellent, thorough reviews of recent developments in neural network control systems, the reader is referred to Miller [1990b] and White and Sofge [ 1992]. 

This chapter presents an overview of the relatively new field of neural network control systems. A variety of techniques are described and some of the advantages and disadvantages of the various techniques are discussed. The techniques described here show great promise for use in biomedical engineering applications in which other control systems techniques are inadequate. Currently, neural network control systems lack the type of theoretical foundation upon which linear control systems are based, but recently... 

Barto, A.G. 1990. Connectionist learning for control an overview. In Neural Networks for Control. 

Table 8.1 Typing oiS. aureus using MALDI-TOF mass spectra and a hierarchical artificial neural network (ANN) overview of the ANN classification results of the external test data set with spectra from S. aureus. The MALDI-TOF-MS-based classification was established by teaching a hierarchical ANN model with mass spectra ofS. aureus fiom six clonal complexes. With the exception of CC8, the data indicated no reliable differentiation between spectra from the individual clonal complexes of y. aureus. Reproduced from Lasch et al. (2014) with permission...

Within the field of chemistry, various applications have already been published. Jansson " and Zupan and Gasteiger published an overview of an MLP (multilayer perceptron), that is trained by back-propagation of errors, and other types of neural networks. However, the basic source in this field continues to be the well-known book of Zupan and Gasteiger." In analytical chemistry, neural networks have been applied to pattern recognition, modeling, and prediction, for example, in multicomponent analysis or process control, to classification, clustering and pattern association. 

The chapter presents a brief overview of the current research on V205/Ti02 catalysts for o-xylene oxidation to phthalic anhydride at Clariant. Phthalic anhydride is produced in tubular, salt-cooled reactors with a capacity of about 5 Mio to per annum. There is a rather broad variety of different process conditions realized in industry in terms of feed composition, air flow rate, as well as reactor dimensions which the phthalic anhydride catalyst portfolio has to match. Catalyst active mass compositions have been optimized at Clariant for these differently realized industry processes utilizing artificial neural networks trained on high-throughput data. Fundamental pilot reactor research unravelling new details of the reaction network of the o-xylene oxidation led to an improved kinetic reactor model which allowed further optimizing of the state of the art multi-layer catalyst system for maximum phthalic anhydride yields. 

Neural augmentation, 29-3-29-8 neural prostheses, 29-3-29-8 sensory prostheses, 29-6-29-8 Neural engineering, history and overview, 29-1-29-12 background, 29-1-29-3 Neural networks adaptive critics in, 12-6-12-7 backpropagation in, 12-4-12-5 basics, 12-2-12-3 in control systems, 12-3-12-7 direct inverse control in, 12-4 for physiological control, 12-1-12-18... 

In this overview section, both traditional statistical methods and the more recent machine-learning methods are briefly surveyed. Excluded here is only the main tool for data analysis and data mining of catalytic materials, i.e., the application of artificial neural networks, to which two of the remaining chapters will be devoted. 

For further information about basic concepts pertaining to artificial neural networks in general, and to multilayer perceptrons in particular, the reader is referred to specialised monographs such as White (1992), Hagan et al. (1996), Mehrotra et al. (1996) and Haykin (1999). An overview of traditional kinds of ANN applications in chemistry can most easily be obtained from the books by Zupan and Gasteiger (1993, 1999), and from the survey papers by Meissen et al. (1994), Smits et al. (1994) and Henson (1998). 

Vapnik, V. (1999). An Overview of Statistical Learning Theory, IEEE Trans, On Neural Networks, 10, pp. 988-999. 

---