Search neural networks

Key words fashion sales forecasting, harmony search, neural network, extreme learning machine. 

Woodruff and co-workers introduced the expert system PAIRS [67], a program that is able to analyze IR spectra in the same manner as a spectroscopist would. Chalmers and co-workers [68] used an approach for automated interpretation of Fourier Transform Raman spectra of complex polymers. Andreev and Argirov developed the expert system EXPIRS [69] for the interpretation of IR spectra. EXPIRS provides a hierarchical organization of the characteristic groups that are recognized by peak detection in discrete ames. Penchev et al. [70] recently introduced a computer system that performs searches in spectral libraries and systematic analysis of mixture spectra. It is able to classify IR spectra with the aid of linear discriminant analysis, artificial neural networks, and the method of fe-nearest neighbors. 

NMR spectra have been predicted using quantum chemistry calculations, database searches, additive methods, regressions, and neural networks. 

H.J. Luinge, E.D. Ixussink, and T. Visser, Trace-level identity confirmation from infrared spectra by library searching and artificial neural networks. Anal. Chim. Acta, 345 (1997) 173-184. 

The search for optima within a given experimental space can also be realized by methodologies different from those that we have discussed before. We want to highlight two of them in this context, namely genetic algorithms and neural networks. 

In many modeling techniques, the number of parameters is modified many times looking for a setting that provides the maximum predictive ability for the model. Techniques for variable selection and methods based on artificial neural networks perform an optimization, that is, they search for conditions able to provide the maximum predictive ability possible for a given sample subset. 

This strategy of integrating neural networks with genetic algorithms has been used to search for the optimal composition of a catalyst for the ammoxidation of propane [62]. In that case, no experiments were performed the network was trained with data published earlier by other authors [63]. However, those data were for only 26 catalysts, thus forming a quite small training set. Even more importantly, the predicted performance of the optimal catalyst, expressed by means of acrylonitrile yield, was not experimentally verified. 

While most combinatorial researches reported up to now involve the use of GA, using the traditional crossover and mutation operators (e.g. WGS 1), it has also been proposed to design new operators for each specific application, to improve search efficiency by means of knowledge extraction [32]. Hence, new methods that combine ES with a knowledge extraction engine have been reported recently within the field of heterogeneous catalysis, such as mining association rules [12, 18, 30, 33] and neural networks [19, 29, 34]. 

Livingstone, D.J. and Salt, D.W., Neural networks in the search for similarity and structure-activity, in P.M. Dean (ed.) Molecular Similarity in Drug Design, Blackie Academic and Professional, Glasgow, 1995, pp. 187-214. 

Another division of neural networks corresponds to the number of layers a simple perception has only one layer (Minski and Papert, 1969), whereas a multilayer perception that has more than one layei (Hertz et al., 1991). This simple differentiation means that network architecture is very important and each application requires its own design. To get good results one should store in the network as much knowledge as possible and use criteria for optimal network architecture as the number of units, the number of connections, the learning time, cost and so on. A genetic algorithm can be used to search the possible architectures (Whitley and Hanson, 1989). 

Whitley, D. and Hanson, T. (1989) Optimizing neural networks using faster more acurate genetic search. Proceedings of Third International Conference on Genetic Algorithms (eds J.D. Schaffer, C.A. San Mateo, and M. Kaufmann), pp. 391-396. 

O Neill, M. C. (1992). Escherichia coli promoters neural networks develop distinct descriptions in learning to search for promoters of different spacing classes. Nucleic Acids Res 20,3471-7. 

Neural network applications for protein sequence analysis are summarized in Table 11.1. Like the DNA coding region recognition problem, signal peptide prediction (11.2) involves both search for content and search for signal tasks. An effective means for protein sequence analysis is reverse database searching to detect functional motifs or sites (11.3) and identify protein families (11.4). Most of the functional motifs are also... 

Signal peptide identification, like DNA intron/exon sequence discrimination, involves the two related problems of signal peptide discrimination (search for content) and cleavage site recognition (search for signal). It is well suited to neural network methods for several reasons. The functional units are encoded by local, linear sequences of amino acids rather than global 3-dimensional structures (Claros et al., 1997). The ambiguity of... 

---