Self-organizing nets

Kohonen networks are also termed self-organizing nets or self-organizing feature maps. 

SONNIA (Self Organizing Neural Network for Information Analysis), http //uww2.chende.uni-eTiangen.de/ softwarefkmap/ and http //www.mol-net.de/... 

Self-organizing ANNs (Kohonen neural nets) were employed for classifying different steels [88]. Twelve relevant elements were selected for data processing through ANNs. 

A specialized method for similarity-based visualization of high-dimensional data is formed by self-organizing feature maps (SOM). The data items are arranged on a two-dimensional plane with the aid of neural networks, especially Kohonen nets. Similarity between data items is represented by spacial closeness, while large distances indicate major dissimilarities [968]. At the authors department, a system called MIDAS had already been developed which combines strategies for the creation of feature maps with the supervised generation of fuzzy-terms from the maps [967]. 

S. Kaski, Data Exploration Using Self-Organizing Maps, Ph.D. Dissertation, Neural Net-... 

CGMD simulations have become a viable tool in studying self-organization processes in catalyst layers of PEFCs. Stmctural parameters of interest for such studies involve composition and size distributions of Pt/C agglomerates, pore space morphology, surface wettability, as well as the structure and distribution of ionomer. The latter aspect has important implications for electrochemically active area, proton transport properties, and net electrocatalytic activity of the CL. 

Neural nets can also be based on unsupervised learning strategies. To date these nets have been employed primarily to support data visualization, but their flexibility is such that they are becoming more common in a wide variety of applications. A simple version of an unsupervised neural net is the Kohonen self-organizing map (SOM) (Kohonen, 1982, 1984 Lang, this volume). These nets also use a set number of nodes, but operate according to different principles. 

Kohonen, T. A Simple Paradigm For The Self-Organized Formatiom Of Structured Feature Maps In Competition And Cooperation In Neural Nets (Lecture notes in biomathematics vol 45, Amari, S. Arbib, M. A. Eds.) ISBN 0387115749 Springer-Verlag Berlin, 1982. 

Organic peroxides and hydroperoxides decompose in part by a self-induced radical chain mechanism whereby radicals released in spontaneous decomposition attack other molecules of the peroxide.The attacking radical combines with one part of the peroxide molecule and simultaneously releases another radical. The net result is the wastage of a molecule of peroxide since the number of primary radicals available for initiation is unchanged. The velocity constant ka we require refers to the spontaneous decomposition only and not to the total decomposition rate which includes the contribution of the chain, or induced, decomposition. Induced decomposition usually is indicated by deviation of the decomposition process from first-order kinetics and by a dependence of the rate on the solvent, especially when it consists of a polymerizable monomer. The constant kd may be separately evaluated through kinetic measurements carried out in the presence of inhibitors which destroy the radical chain carriers. The aliphatic azo-bis-nitriles offer a real advantage over benzoyl peroxide in that they are not susceptible to induced decomposition. 

Contributions to fcobs from diffusional effects are only numerically significant for reactions which approach within a factor of 10 of the diffusion-controlled limit. From the data in Table 1, only a few self-exchange cases, e.g. Ru(bipy)33+/2+ and some of the organic couples, approach this limit although it is a common feature for net reactions where AG is highly favorable and X small. 

---