Neural networks supervised learning

In the early days of catalyst screening, speed was the only important matter. This meant collecting as much information as possible on a certain catalyst under defined process parameters. This approach produces a large number of non-interrelated single data points with a low degree of information. As soon as correlations between these data can be found, the information density increases. This is the case if reaction kinetics are derived from single data points or if a supervised artificial neural network has learned to predict relations between data points. 

A counter-propagation neural network is a method for supervised learning which can be used for predictions. 

As described in the Introduction to this volume (Chapter 28), neural networks can be used to carry out certain tasks of supervised or unsupervised learning. In particular, Kohonen mapping is related to clustering. It will be explained in more detail in Chapter 44. 

Indeed, if the problem is simple enough that the connection weights can be found by a few moments work with pencil and paper, there are other computational tools that would be more appropriate than neural networks. It is in more complex problems, in which the relationships that exist between data points are unknown so that it is not possible to determine the connection weights by hand, that an ANN comes into its own. The ANN must then discover the connection weights for itself through a process of supervised learning. 

Fritzke, B. (1994) Growing cell structures-a self-organizing network for unsupervised and supervised learning. Neural Networks 7 1441-1460... 

More complex approaches to this problem involve the use of artificial neural networks [22], Bayesian networks [23] and support vector machines [24], which in turn are based on the same principle of supervised learning [25]. 

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. 

There are literally dozens of kinds of neural network architectures in use. A simple taxonomy divides them into two types based on learning algorithms (supervised, unsupervised) and into subtypes based upon whether they are feed-forward or feedback type networks. In this chapter, two other commonly used architectures, radial basis functions and Kohonen self-organizing architectures, will be discussed. Additionally, variants of multilayer perceptrons that have enhanced statistical properties will be presented. 

Mailer, M. (1993). A scaled conjugate gradient algorithm for fast supervised learning. Neural Networks 6,525-33. 

One other network that has been used with supervised learning is the radial basis function (RBF) network.f Radial functions are relatively simple in form, and by definition must increase (or decrease) monotonically with the distance from a certain reference point. Gaussian functions are one example of radial functions. In a RBF network, the inputs are fed to a layer of RBFs, which in turn are weighted to produce an output from the network. If the RBFs are allowed to move or to change size, or if there is more than one hidden layer, then the RBF network is non-linear. An RBF network is shown schematically for the case of n inputs and m basis functions in Fig. 3. The generalized regression neural network, a special case of the RBF network, has been used infrequently especially in understanding in vitro-in vivo correlations. 

---