Neural network performance

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. 

By selectively changing sequences in E. coli translation initiation region with randomized calliper inputs and observing the corresponding neural network performance, Nair (1997) analyzed the importance of the initiation codon and the Shine-Dalgamo sequence. 

The basic feedforward neural network performs a non-linear transformation of the input data in order to approximate the output data. This net is composed of many simple, locally interacting, computational elements (nodes/neurons), where each node works as a simple processor. The schematic diagram of a single neuron is shown in Fig 1. The input to each i-th neuron consists of a A-dimensional vector X and a single bias (threshold) bj. Each of the input signals Xj is weighted by the appropiate weight Wij, where] = 1- N. 

The supervised artificial neural network has proved to be an effective classifier in which the probabihstic neural network performs better than in the other networks on the site selection problem. 

A neural network performs parallel and distributed information processing that is learned from examples, and can hence be used for complex bioimpedance signal processing. 

Indices for the Evaluation of Neural Network Performances as Classifier Application to Structural Elucidation in Infrared Spectroscopy. 

M. L. Meistrell and K. A. Spackman, Proceedings of the 13 th Annual Symposium on Computer Applications in Medical Care, Washington, DC, 1989, pp. 295-301. Evaluation of Neural Network Performance by Receiver Operating Characteristic Analysis Examples from the Biotechnology Domain. 

Data collection. Neural networks perform best with a large amount of data. The more data, the better the network s performance is likely to be. 

Fuzzy theory can be applied to determine the desired control force to be applied by the actuator. Neural network performance function selection can be used in structural control (Casciati et al. 1993). 

Casciati F, Faravelli L, Venini P (1993) A neural-network performance-function selection in active structural control. In Proceedings of the international workshop on structural control. University of Southern California, Los Angeles... 

The results obtained with NSC in different applications show that both flaw detection and localization can be performed automatically by the use of a neural network classifier. 

Problems involving routine calculations are solved much faster and more reliably by computers than by humans. Nevertheless, there are tasks in which humans perform better, such as those in which the procedure is not strictly determined and problems which are not strictly algorithmic. One of these tasks is the recognition of patterns such as feces. For several decades people have been trying to develop methods which enable computers to achieve better results in these fields. One approach, artificial neural networks, which model the functionality of the brain, is explained in this section. 

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. 

Neural networks have been applied to IR spectrum interpreting systems in many variations and applications. Anand [108] introduced a neural network approach to analyze the presence of amino acids in protein molecules with a reliability of nearly 90%. Robb and Munk [109] used a linear neural network model for interpreting IR spectra for routine analysis purposes, with a similar performance. Ehrentreich et al. [110] used a counterpropagation network based on a strategy of Novic and Zupan [111] to model the correlation of structures and IR spectra. Penchev and co-workers [112] compared three types of spectral features derived from IR peak tables for their ability to be used in automatic classification of IR spectra. 

In many cases, structure elucidation with artificial neural networks is limited to backpropagation networks [113] and, is therefore performed in a supervised man-... 

Neural networks have been proposed as an alternative way to generate quantitative structure-activity relationships [Andrea and Kalayeh 1991]. A commonly used type of neural net contains layers of units with connections between all pairs of units in adjacent layers (Figure 12.38). Each unit is in a state represented by a real value between 0 and 1. The state of a unit is determined by the states of the units in the previous layer to which it is connected and the strengths of the weights on these connections. A neural net must first be trained to perform the desired task. To do this, the network is presented with a... 

Eor a number of cognitive or interpretive tasks, there are alternatives to mainstream knowledge-based systems that may be more appropriate, especially if adaptive behavior and learning capabihty are important to system performance. Two approaches that embody these characteristics are neural networks (nets) and case-based reasoning. 

The first is the relational model. Examples are hnear (i.e., models linear in the parameters and neural network models). The model output is related to the input and specifications using empirical relations bearing no physical relation to the actual chemical process. These models give trends in the output as the input and specifications change. Actual unit performance and model predictions may not be very close. Relational models are usebil as interpolating tools. 

Intended Use The intended use of the model sets the sophistication required. Relational models are adequate for control within narrow bands of setpoints. Physical models are reqiiired for fault detection and design. Even when relational models are used, they are frequently developed bv repeated simulations using physical models. Further, artificial neural-network models used in analysis of plant performance including gross error detection are in their infancy. Readers are referred to the work of Himmelblau for these developments. [For example, see Terry and Himmelblau (1993) cited in the reference list.] Process simulators are in wide use and readily available to engineers. Consequently, the emphasis of this section is to develop a pre-liminaiy physical model representing the unit. 

In neural network design, the above parameters have no precise number/answers because it is dependent on the particular application. However, the question is worth addressing. In general, the more patterns and the fewer hidden neurons to be used, the better the network. It should be realized that there is a subtle relationship between the number of patterns and the number of hidden layer neurons. Having too few patterns or too many hidden neurons can cause the network to memorize. When memorization occurs, the network would perform well during training, but tests poorly with a new data set. 

Topical Formulations. Topical formulations by their very nature are usually multicomponent, and it is not surprising that neural networks have been applied to deal with this complexity. The first work was performed on hydrogel formulations containing anti-inflammatory drugs in Japan in 1997 [57], followed up by further studies in 1999 [58] and in 2001 [59]. Lipophilic semisolid emulsion systems have been studied in Slovenia [60, 61] and transdermal delivery formulations of melatonin in Florida [62]. In all cases, the superiority of neural networks over conventional statistics has been reported. 

---