Weizmann Logo
ECCC
Electronic Colloquium on Computational Complexity

Under the auspices of the Computational Complexity Foundation (CCF)

Login | Register | Classic Style



REPORTS > DETAIL:

Paper:

TR04-033 | 23rd January 2004 00:00

On the sample complexity of learning for networks of spiking neurons with nonlinear synaptic interactions

RSS-Feed




TR04-033
Authors: Michael Schmitt
Publication: 10th April 2004 16:19
Downloads: 1506
Keywords: 


Abstract:

We study networks of spiking neurons that use the timing of pulses
to encode information. Nonlinear interactions model the spatial
groupings of synapses on the dendrites and describe the computations
performed at local branches. We analyze the question of how many
examples these networks must receive during learning to be able to
generalize well. Bounds for this sample complexity of learning are
derived in terms of the pseudo-dimension. In particular, we obtain
almost linear and quadratic upper bounds in terms of the number of
adjustable parameters for depth-restricted and general feedforward
architectures, respectively. These bounds are also shown to be
asymptotically tight for networks that satisfy realistic
constraints.



ISSN 1433-8092 | Imprint