Self-organized learning

An observation of the results of cross-validation revealed that all but one of the compounds in the dataset had been modeled pretty well. The last (31st) compound behaved weirdly. When we looked at its chemical structure, we saw that it was the only compound in the dataset which contained a fluorine atom. What would happen if we removed the compound from the dataset The quahty ofleaming became essentially improved. It is sufficient to say that the cross-vahdation coefficient in-CTeased from 0.82 to 0.92, while the error decreased from 0.65 to 0.44. Another learning method, the Kohonen s Self-Organizing Map, also failed to classify this 31st compound correctly. Hence, we had to conclude that the compound containing a fluorine atom was an obvious outlier of the dataset. 

Now, one may ask, what if we are going to use Feed-Forward Neural Networks with the Back-Propagation learning rule Then, obviously, SVD can be used as a data transformation technique. PCA and SVD are often used as synonyms. Below we shall use PCA in the classical context and SVD in the case when it is applied to the data matrix before training any neural network, i.e., Kohonen s Self-Organizing Maps, or Counter-Propagation Neural Networks. 

The self-organization or assembly of nnits at the nanoscale to form supramolecnlar ensembles on mesoscopic length scales comprises the range of colloidal systems. There is a need to understand the connection between structure and properties, the evolution and dynamics of these structures at the different levels—supramolecnlar, molecular, and sub-molecular— by learning from below. ... 

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. 

Chirality is an essential property of life, which can be found throughout all biological self-assembled and self-organized architectures. Over many millennia nature has, through trial and error, learned how to utilize the chiral properties of the small building blocks, for example, amino acids and nucleic acids and how to express this structural property in a hierarchical process at the quaternary level. This expression of chirality at the quaternary level in turn... 

Methods for unsupervised learning invariably aim at compression or the extraction of information present in the data. Most prominent in this field are clustering methods [140], self-organizing networks [141], any type of dimension reduction (e.g., principal component analysis [142]), or the task of data compression itself. All of the above may be useful to interpret and potentially to visualize the data. 

A self-organizing Kohonen map of the total database of cleaved retrosynthetic fragments generated as the result of an unsupervised learning procedure (data not shown)indicates that the cleaved fragments occupy a wide area on the map, characterized... 

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. 

The spontaneous emergence of order at critical points of instability is one of the most important concepts of the new understanding of life. It is technically known as self-organization and is often referred to simply as emergence . It has been recognized as the dynamic origin of development, learning and evolution. 

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

Unsupervised multivariate statistical methods [CA, principal components analysis, Kohonen s self-organizing maps (SOMs), nonlinear mapping, etc.], which perform spontaneous data analysis without the need for special training (learning), levels of knowledge, or preliminary conditions. 

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. 

---