论文信息 - The Euclidean Memory Array — A vector quantisation technique for the processing of data from interview forms

The Euclidean Memory Array — A vector quantisation technique for the processing of data from interview forms

In this paper, work that has been carried out on the processing of data derived from interview forms is discussed. Various attempts have been made to process the data using Kohonen self-organising maps. The object of the processing was to identify both local and global trends within the data sets. The difficulty encountered in training the networks and interpreting the results led to the development of a new vector quantisation network, the ‘Euclidean Memory Array’, a network made distinct by the lack of a conventional learning process. This technique provided a valuable insight into the trends within the data, proving effective even on extremely small data sets.

[1] J. Fort. Solving a combinatorial problem via self-organizing process: An application of the Kohonen algorithm to the traveling salesman problem , 1988, Biological Cybernetics.

[2] Patrick K. Simpson,et al. Artificial Neural Systems: Foundations, Paradigms, Applications, and Implementations , 1990 .

[3] A. J. Surkan. Application of neural networks to classification of binary profiles derived from individual interviews , 1988, IEEE 1988 International Conference on Neural Networks.

[4] Teuvo Kohonen,et al. Self-organization and associative memory: 3rd edition , 1989 .

[5] Pentti Kanerva,et al. Sparse Distributed Memory , 1988 .

[6] Z. Zhao,et al. Use of Kohonen self-organising feature maps for HMM parameter smoothing in speech recognition , 1992 .

[7] Olivier Sarzeaud,et al. FINITE ELEMENT MESHING USING KOHONEN'S SELF-ORGANIZING MAPS , 1991 .

[8] Judith E. Dayhoff,et al. Neural Network Architectures: An Introduction , 1989 .

[9] Geoffrey E. Hinton,et al. Learning internal representations by error propagation , 1986 .

[10] J. Penman,et al. Using Kohonen Feature Maps To Monitor The Condition Of Synchronous Generators , 1993, Workshop on Neural Network Applications and Tools.

[11] T. Kohonen,et al. Statistical pattern recognition with neural networks: benchmarking studies , 1988, IEEE 1988 International Conference on Neural Networks.