Self-organizing networks

Ding, J., Chuy, C. and Holdcroft, S. 2001. A self-organized network of nanochannels enhances ion conductivity through polymer films. Chemistry of Materials 13 2231-2233. 

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. 

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

Figure 8.13 Structure of self-organizing networks in linear arrangement (a) of the competitive layer and in Kohonen representation (b).

Govor, L.V., Bashmakov, I.A., Kiebooms, R., Dyakonov, V., Parisi, J. Self-organized networks based on conjugated polymers. Adv. Mater. 13, 588-591 (2001)... 

Self-organizing networks The neurones are organized on a sort of dynamic map that evolves during the learning process, in a way that is sensitive to the history and neighboring neurones. Clustering of input data is used to extract extra information from the data. 

J. Rubner and P. Tavan, Europhys. Lett., 10, 693 (1989). A Self-Organizing Network for Principal-Component Analysis. 

Ashkenasy et al. have used the scoring method and reported the design, graph estimation, and analyses of a relatively simple synthetic molecular system." This system seems to bear some of the basic properties that can be attributed to complex self-organized networks such as reciprocal replication, central nodes, and functional subnetwork... 

Figure 7 A 9-mer network bearing some basic propraties attributed to complex self-organized networks such as reciprocal replication, central node, and subnetwork. The arrows (edges) designate template-assisted ligation pathways pointing from the template to the product, the and arrows circling a template represent autocatalysis. The network represents compilation of the results of four studies, and the colors of the lines represent a group of data obtained in the different studies (see text).

These phenomena, together with the enhanced affinity toward the substrate (the association constant increases of almost four orders of magnitude in the NPs), induced by the self-organized network on the surface of the nanoparticles, lead to a great increase in the sensitivity of the system, and provide interesting hints for the development of new fluorescent chemosensors. The same TSQ derivative was included in the silica matrix by Mancin and coworkers [25] that reported how its fluorescence was still sensitive to the presence of zinc ions but no amphfication effect could be observed, as we will discuss more in detail in Sect. 3.1.2. 

Fritzke, B. (1997) A self-organizing network that can follow non-stationary distributions. In International Conference on Neural Networks (eds W. Gerstnre et al.), Springer-Verlag, Lausanne, pp. 613-618. 

Similarly P-P, meso-meso, P-P triply linked dimers were obtained by Diederich and CO workers. They showed that such dimers led to weU-organized self-assembled networks on silver surfaces [162, 163]. Similar self-organized networks were observed for hybrid Ceo-triply linked dimer assemblies [162, 163]. Hybrid assemblies between single-walled carbon nanotubes (SWNTs) and triply linked trimers were also investigated and allowed the formation of stable supramolecular carbon nanotubes-porphyrin complexes [164]. 

---