We present a neural net algorithm for parameter estimation in the context of
large cosmological data sets. Cosmological data sets present a particular
challenge to pattern-recognition algorithms since the input patterns (galaxy
redshift surveys, maps of cosmic microwave background anisotropy) are not fixed
templates overlaid with random noise, but rather are random realizations whose
information content lies in the correlations between data points. We train a
``committee'' of neural nets to distinguish between Monte Carlo simulations at
fixed parameter values. Sampling the trained networks using additional Monte
Carlo simulations generated at intermediate parameter values allows accurate
interpolation to parameter values for which the networks were never trained.
The Monte Carlo samples automatically provide the probability distributions and
truth tables required for either a frequentist or Bayseian analysis of the one
observable sky. We demonstrate that neural networks provide unbiased parameter
estimation with comparable precision as maximum-likelihood algorithms but
significant computational savings. In the context of CMB anisotropies, the
computational cost for parameter estimation via neural networks scales as
\$N^3/2\$. The results are insensitive to the noise levels and sampling schemes
typical of large cosmological data sets and provide a desirable tool for the
new generation of large, complex data sets.
%0 Journal Article
%1 Phillips2001Neural
%A Phillips, Nicholas G.
%A Kogut, A.
%D 2001
%K neural
%T Neural networks as a tool for parameter estimation in astrophysical data
%U http://arxiv.org/abs/astro-ph/0112359
%X We present a neural net algorithm for parameter estimation in the context of
large cosmological data sets. Cosmological data sets present a particular
challenge to pattern-recognition algorithms since the input patterns (galaxy
redshift surveys, maps of cosmic microwave background anisotropy) are not fixed
templates overlaid with random noise, but rather are random realizations whose
information content lies in the correlations between data points. We train a
``committee'' of neural nets to distinguish between Monte Carlo simulations at
fixed parameter values. Sampling the trained networks using additional Monte
Carlo simulations generated at intermediate parameter values allows accurate
interpolation to parameter values for which the networks were never trained.
The Monte Carlo samples automatically provide the probability distributions and
truth tables required for either a frequentist or Bayseian analysis of the one
observable sky. We demonstrate that neural networks provide unbiased parameter
estimation with comparable precision as maximum-likelihood algorithms but
significant computational savings. In the context of CMB anisotropies, the
computational cost for parameter estimation via neural networks scales as
\$N^3/2\$. The results are insensitive to the noise levels and sampling schemes
typical of large cosmological data sets and provide a desirable tool for the
new generation of large, complex data sets.
@article{Phillips2001Neural,
abstract = {We present a neural net algorithm for parameter estimation in the context of
large cosmological data sets. Cosmological data sets present a particular
challenge to pattern-recognition algorithms since the input patterns (galaxy
redshift surveys, maps of cosmic microwave background anisotropy) are not fixed
templates overlaid with random noise, but rather are random realizations whose
information content lies in the correlations between data points. We train a
``committee'' of neural nets to distinguish between Monte Carlo simulations at
fixed parameter values. Sampling the trained networks using additional Monte
Carlo simulations generated at intermediate parameter values allows accurate
interpolation to parameter values for which the networks were never trained.
The Monte Carlo samples automatically provide the probability distributions and
truth tables required for either a frequentist or Bayseian analysis of the one
observable sky. We demonstrate that neural networks provide unbiased parameter
estimation with comparable precision as maximum-likelihood algorithms but
significant computational savings. In the context of CMB anisotropies, the
computational cost for parameter estimation via neural networks scales as
\$N^{3/2}\$. The results are insensitive to the noise levels and sampling schemes
typical of large cosmological data sets and provide a desirable tool for the
new generation of large, complex data sets.},
added-at = {2019-02-23T22:09:48.000+0100},
archiveprefix = {arXiv},
author = {Phillips, Nicholas G. and Kogut, A.},
biburl = {https://www.bibsonomy.org/bibtex/2a8e0a8afa203ca9533a78b2d9493d084/cmcneile},
citeulike-article-id = {7132503},
citeulike-linkout-0 = {http://arxiv.org/abs/astro-ph/0112359},
citeulike-linkout-1 = {http://arxiv.org/pdf/astro-ph/0112359},
day = 14,
eprint = {astro-ph/0112359},
interhash = {6a629b09ac320ade26356227ef459705},
intrahash = {a8e0a8afa203ca9533a78b2d9493d084},
keywords = {neural},
month = dec,
posted-at = {2010-05-06 16:37:52},
priority = {2},
timestamp = {2019-02-23T22:15:27.000+0100},
title = {{Neural networks as a tool for parameter estimation in astrophysical data}},
url = {http://arxiv.org/abs/astro-ph/0112359},
year = 2001
}