Unsupervised clustering with spiking neurons by sparse temporal coding and multi-layer {RBF} networks

TitleUnsupervised clustering with spiking neurons by sparse temporal coding and multi-layer {RBF} networks
Publication TypeBook Chapter
Year of Publication2000
AuthorsBohte SM, Poutre LJA, Kok JN
Book Title2435
Pagination14
PublisherCentrum voor Wiskunde en Informatica (CWI)
CityISSN 1386-369X
Keywordscoarse coding., complex clusters, Hebbian-learning, high-dimensional clustering, sparse coding, spiking neurons, synchronous firing, temporal coding, unsupervised learning
AbstractWe demonstrate that spiking neural networks encoding information in spike times are capable of computing and learning clusters from realistic data. We show how a spiking neural network based on spike-time coding and Hebbian learning can successfully perform unsupervised clustering on real-world data, and we demonstrate how temporal synchrony in a multi-layer network induces hierarchical clustering. We develop a temporal encoding of continuously valued data to obtain adjustable clustering capacity and precision with an efficient use of neurons: input variables are encoded in a population code by neurons with graded and overlapping sensitivity profiles. We also discuss methods for enhancing scale-sensitivity of the network and show how induced synchronization of neurons within early RBF layers allows for the subsequent detection of complex clusters.
URLhttp://www.cwi.nl/ftp/CWIreports/SEN/SEN-R0036.ps.Z