Title :
Multimodality exploration by an unsupervised projection pursuit neural network
Author :
Dotan, Yocheved ; Intrator, Nathan
Author_Institution :
Dept. of Comput. Sci., Tel Aviv Univ., Israel
fDate :
5/1/1998 12:00:00 AM
Abstract :
Graphical inspection of multimodality is demonstrated using unsupervised lateral-inhibition neural networks. Three projection pursuit indexes are compared on low-dimensional simulated and real-world data: principal components, Legendre polynomial, and projection pursuit network
Keywords :
Legendre polynomials; neural nets; pattern recognition; statistical analysis; unsupervised learning; Legendre polynomial; graphical inspection; multimodality exploration; principal components; projection pursuit indexes; unsupervised lateral-inhibition neural networks; unsupervised projection pursuit neural network; Computer science; Data analysis; Density functional theory; Inspection; Kernel; Neural networks; Polynomials; Robustness; Scattering; Unsupervised learning;
Journal_Title :
Neural Networks, IEEE Transactions on