Networks of spiking neurons: the third generation of neural network models
W. Maass. Trans. Soc. Comput. Simul. Int., 14 (4):
1659--1671(1997)
Zusammenfassung
The computational power of formal models for networks of spiking neurons is compared with that of other
neural network models based on McCulloch Pitts neurons (i.e., threshold gates), respectively, sigmoidal gates. In
particular it is shown that networks of spiking neurons are, with regard to the number of neurons that are needed,
computationally more powerful than these other neural network models. A concrete biologically relevant function is
exhibited which can be computed by a single spiking neuron (for biologically reasonable values of its parameters), but
which requires hundreds of hidden units on a sigmoidal neural net. On the other hand, it is known that any function that
can be computed by a small sigmoidal neural net can also be computed by a small network of spiking neurons. This
article does not assume prior knowledge about spiking neurons, and it contains an extensive list of references to the
currently available literature on computations in networks of spiking neurons and relevant results from neurobiology.
Beschreibung
Networks of spiking neurons: the third generation of neural network models
%0 Journal Article
%1 Maass
%A Maass, Wofgang
%C San Diego, CA, USA
%D 1997
%I Society for Computer Simulation International
%J Trans. Soc. Comput. Simul. Int.
%K imported
%N 4
%P 1659--1671
%T Networks of spiking neurons: the third generation of neural network models
%U http://portal.acm.org/citation.cfm?id=281637
%V 14
%X The computational power of formal models for networks of spiking neurons is compared with that of other
neural network models based on McCulloch Pitts neurons (i.e., threshold gates), respectively, sigmoidal gates. In
particular it is shown that networks of spiking neurons are, with regard to the number of neurons that are needed,
computationally more powerful than these other neural network models. A concrete biologically relevant function is
exhibited which can be computed by a single spiking neuron (for biologically reasonable values of its parameters), but
which requires hundreds of hidden units on a sigmoidal neural net. On the other hand, it is known that any function that
can be computed by a small sigmoidal neural net can also be computed by a small network of spiking neurons. This
article does not assume prior knowledge about spiking neurons, and it contains an extensive list of references to the
currently available literature on computations in networks of spiking neurons and relevant results from neurobiology.
@article{Maass,
abstract = {The computational power of formal models for networks of spiking neurons is compared with that of other
neural network models based on McCulloch Pitts neurons (i.e., threshold gates), respectively, sigmoidal gates. In
particular it is shown that networks of spiking neurons are, with regard to the number of neurons that are needed,
computationally more powerful than these other neural network models. A concrete biologically relevant function is
exhibited which can be computed by a single spiking neuron (for biologically reasonable values of its parameters), but
which requires hundreds of hidden units on a sigmoidal neural net. On the other hand, it is known that any function that
can be computed by a small sigmoidal neural net can also be computed by a small network of spiking neurons. This
article does not assume prior knowledge about spiking neurons, and it contains an extensive list of references to the
currently available literature on computations in networks of spiking neurons and relevant results from neurobiology.
},
added-at = {2007-11-05T22:14:54.000+0100},
address = {San Diego, CA, USA},
author = {Maass, Wofgang},
biburl = {https://www.bibsonomy.org/bibtex/2a4d641a35f83a12954f8eb51cf28e58f/tmalsburg},
description = {Networks of spiking neurons: the third generation of neural network models},
interhash = {a8621a10729f344463f031791f7ed88f},
intrahash = {a4d641a35f83a12954f8eb51cf28e58f},
issn = {0740-6797},
journal = {Trans. Soc. Comput. Simul. Int.},
keywords = {imported},
number = 4,
pages = {1659--1671},
publisher = {Society for Computer Simulation International},
timestamp = {2007-11-05T22:14:54.000+0100},
title = {Networks of spiking neurons: the third generation of neural network models},
url = {http://portal.acm.org/citation.cfm?id=281637},
volume = 14,
year = 1997
}