Paper available: hebbian learning with time spikes

[Sander Bohte]

The following paper, on computing with precisely times spiking neurons,
is available from  
http://www.cwi.nl/~sbohte/publication/usnnrep.pdf
or from
http://www.cwi.nl/~sbohte/pub_usnn2k2.htm

S.M. Bohte, H. La Poutre and J.N. Kok (2002).  "Unsupervised Clustering
with Spiking Neurons by Sparse Temporal Coding and Multi-Layer RBF
Networks."  This is a final draft of a paper that will appear in IEEE
Transactions on Neural Networks (2002).

Abstract:

We demonstrate that spiking neural networks encoding information in the
timing of single spikes 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 can induce 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 the induced synchronization of neurons within early RBF layers
allows for the subsequent detection of complex clusters.

Keywords:
Spiking neurons, unsupervised learning, high-dimensional clustering,
complex clusters, Hebbian-learning, synchronous firing, sparse coding,
temporal coding, coarse coding.

Sander


=====================================
Sander Bohte	
The Netherlands Center for Mathematics and Computer Science (CWI)
Dept SEN4			tel: +31-20 592 4926
Kruislaan 413		fax: +31-20 592 4199
NL-1098 SJ Amsterdam	www: http://www.cwi.nl/~sbohte
The Netherlands		mail: sbohte at cwi.nl