Figure 1. Absorption spectra of the assembly at each stage of the transformation. For clarity, the PSS-CdS-Au spectrum has been shifted vertically by 0.5 units. The change in the color of the solution, from wine red to violet blue and then muddy yellow, is visible in the photograph.
Self-organization of a one-dimensional Kohonen network with quantized weights and inputs
โ Scribed by Patrick Thiran; Martin Hasler
- Publisher
- Elsevier Science
- Year
- 1994
- Tongue
- English
- Weight
- 998 KB
- Volume
- 7
- Category
- Article
- ISSN
- 0893-6080
No coin nor oath required. For personal study only.
โฆ Synopsis
If a self-organizing neural network has to be implemented on a digital (or mixed analog and digital) circuit realization, with on-chip learning, all the input signals and the weight values have to be quantized. It is therefore crucial to study whether this quantization does not annihilate the self-organization property of the weights. This paper provides necessary and sufficient conditions on the parameters of a one-dimensional network, which ensure the organization of the weights for any one-dimensional input probability distribution. These results are rigorously proved using the Markovian formulation of Kohonen's algorithm.
๐ SIMILAR VOLUMES
The current interest in the crystal engineering of polymeric coordination networks [1] stems from their potential applications as zeolite-like materials for molecular selection, ion exchange, and catalysis, as well as in the intriguing variety of architectures and topologies. Particularly attractiv