Self-learning algorithms

This results in a light pulse with a time profile that depends on the phase differences between its spectral components, which in turn can be controlled by the LCD, driven by a special computer program (Fig. 11.34) [11.81,11.82]. A self-learning algorithm can be incorporated into the closed loop, which compares the output pulse form with the wanted one and tries to vary the voltage at the different pixels in such a way that the wanted pulse form is approximated [11.83]. More details can be found in [11.84]... 

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. 

Nerrand, O., Roussel-Ragot, R, Personnaz, L., Dreyfus, G., and Marcos, S. 1993. Neural networks and nonlinear adaptive filtering Unifying concepts and new algorithms. Neural Comput., 5 165-199. Nguyen, D.H. and Widrow, B. 1990. Neural networks for self-learning control systems. IEEE Contr. Syst. Mag., 10(3) 18-23. 

As we saw in the previous chapter, self-organizing maps (SOMs) are a powerful way to reveal the clustering of multidimensional samples. The two-dimensional SOM is often able to provide an informative separation of samples into classes and the learning in which it engages requires no input from the user, beyond the initial selection of parameters that define the scale of the mapping and the way that the algorithm operates. 

The growing cell structure algorithm is a variant of a Kohonen network, so the GCS displays several similarities with the SOM. The most distinctive feature of the GCS is that the topology is self-adaptive, adjusting as the algorithm learns about classes in the data. So, unlike the SOM, in which the layout of nodes is regular and predefined, the GCS is not constrained in advance to a particular size of network or a certain lattice geometry. 

It can be shown that the unsupervised learning methodology based on Kohonen self-organizing maps algorithm can be effectively used for differentiation between various receptor-specific groups of GPCR ligands. The method is similar to that described in Section 12.2.6. 

Kohonen self-organizing map An unsupervised learning method of clustering, based on the k-means algorithm, similar to the first stage of radial basis function networks. Self-organized maps are used for classification and clustering. 

---