% IMPORTANT: The following is UTF-8 encoded. This means that in the presence
% of non-ASCII characters, it will not work with BibTeX 0.99 or older.
% Instead, you should use an up-to-date BibTeX implementation like “bibtex8” or
% “biber”.
@ARTICLE{Dahmen:874632,
author = {Dahmen, David and Gilson, Matthieu and Helias, Moritz},
title = {{C}apacity of the covariance perceptron},
journal = {Journal of physics / A},
volume = {53},
number = {35},
issn = {0022-3689},
address = {Bristol},
publisher = {IOP Publ.},
reportid = {FZJ-2020-01552},
pages = {354002},
year = {2020},
abstract = {The classical perceptron is a simple neural network that
performs a binary classification by a linear mapping between
static inputs and outputs and application of a threshold.
For small inputs, neural networks in a stationary state also
perform an effectively linear input-output transformation,
but of an entire time series. Choosing the temporal mean of
the time series as the feature for classification, the
linear transformation of the network with subsequent
thresholding is equivalent to the classical perceptron. Here
we show that choosing covariances of time series as the
feature for classification maps the neural network to what
we call a 'covariance perceptron'; a mapping between
covariances that is bilinear in terms of weights. By
extending Gardner's theory of connections to this bilinear
problem, using a replica symmetric mean-field theory, we
compute the pattern and information capacities of the
covariance perceptron in the infinite-size limit.
Closed-form expressions reveal superior pattern capacity in
the binary classification task compared to the classical
perceptron in the case of a high-dimensional input and
low-dimensional output. For less convergent networks, the
mean perceptron classifies a larger number of stimuli.
However, since covariances span a much larger input and
output space than means, the amount of stored information in
the covariance perceptron exceeds the classical counterpart.
For strongly convergent connectivity it is superior by a
factor equal to the number of input neurons. Theoretical
calculations are validated numerically for finite size
systems using a gradient-based optimization of a
soft-margin, as well as numerical solvers for the NP hard
quadratically constrained quadratic programming problem, to
which training can be mapped.},
cin = {INM-6 / IAS-6 / INM-10},
ddc = {530},
cid = {I:(DE-Juel1)INM-6-20090406 / I:(DE-Juel1)IAS-6-20130828 /
I:(DE-Juel1)INM-10-20170113},
pnm = {571 - Connectivity and Activity (POF3-571) / 574 - Theory,
modelling and simulation (POF3-574) / MSNN - Theory of
multi-scale neuronal networks (HGF-SMHB-2014-2018) / HBP
SGA2 - Human Brain Project Specific Grant Agreement 2
(785907) / neuroIC002 - Recurrence and stochasticity for
neuro-inspired computation (EXS-SF-neuroIC002)},
pid = {G:(DE-HGF)POF3-571 / G:(DE-HGF)POF3-574 /
G:(DE-Juel1)HGF-SMHB-2014-2018 / G:(EU-Grant)785907 /
G:(DE-82)EXS-SF-neuroIC002},
typ = {PUB:(DE-HGF)16},
UT = {WOS:000561625100001},
doi = {10.1088/1751-8121/ab82dd},
url = {https://juser.fz-juelich.de/record/874632},
}