% 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”.
@INPROCEEDINGS{Fischer:910329,
author = {Fischer, Kirsten and Rene, Alexandre and Keup, Christian
and Layer, Moritz and Dahmen, David and Helias, Moritz},
title = {{S}tatistical decomposition of feed-forward neural
networks: {T}ransfer of information between correlation
functions},
reportid = {FZJ-2022-03755},
year = {2022},
abstract = {Uncovering principles of information processing in neural
systems continues to be an active field of research. For the
visual system it is well known that it processes signals in
a hierarchical manner [1,2]. Feed-forward networks are
commonly used models in machine learning that perform
hierarchical computations. We here study deep feed-forward
networks with the aim of deducing general functional aspects
of such systems. These networks implement mappings between
probability distributions, where the probability
distribution are iteratively transformed from layer to
layer. We develop a formalism for expressing signal
transformations in each layer as information transfers
between different orders of correlation functions. We show
that the processing within internal network layers is
captured by correlations up to second order. In addition, we
demonstrate how the input layer also extracts higher order
correlations from the data. Thus, by presenting different
correlation orders in the input, we identify key statistics
in the data. As a next step, we consider recurrent
time-continuous networks, reminiscent of biological neuronal
networks (NeuralODEs, [3]). We derive a Fokker-Planck
equation describing the evolution of the probability
distribution. This formulation allows us to study
time-dependent information flow between different
interaction terms. In summary, this work provides insights
into functional principles of information processing in
neural networks.References[1] Hubel, D. H., $\&$ Wiesel, T.
N. (1962). Receptive fields, binocular interaction and
functional architecture in the cat's visual cortex. The
Journal of physiology, 160(1), 106.[2] Zhuang, C., Yan, S.,
Nayebi, A., Schrimpf, M., Frank, M. C., DiCarlo, J. J., $\&$
Yamins, D. L. (2021). Unsupervised neural network models of
the ventral visual stream. Proceedings of the National
Academy of Sciences, 118(3), e2014196118.[3] Chen, R. T.,
Rubanova, Y., Bettencourt, J., $\&$ Duvenaud, D. K. (2018).
Neural ordinary differential equations. Advances in neural
information processing systems, 31.},
month = {Oct},
date = {2022-10-18},
organization = {INM IBI Retreat 2022, Juelich
(Germany), 18 Oct 2022 - 19 Oct 2022},
subtyp = {After Call},
cin = {INM-6 / IAS-6 / INM-10},
cid = {I:(DE-Juel1)INM-6-20090406 / I:(DE-Juel1)IAS-6-20130828 /
I:(DE-Juel1)INM-10-20170113},
pnm = {5232 - Computational Principles (POF4-523) / 5234 -
Emerging NC Architectures (POF4-523) / RenormalizedFlows -
Transparent Deep Learning with Renormalized Flows
(BMBF-01IS19077A) / MSNN - Theory of multi-scale neuronal
networks (HGF-SMHB-2014-2018) / ACA - Advanced Computing
Architectures (SO-092) / neuroIC002 - Recurrence and
stochasticity for neuro-inspired computation
(EXS-SF-neuroIC002)},
pid = {G:(DE-HGF)POF4-5232 / G:(DE-HGF)POF4-5234 /
G:(DE-Juel-1)BMBF-01IS19077A /
G:(DE-Juel1)HGF-SMHB-2014-2018 / G:(DE-HGF)SO-092 /
G:(DE-82)EXS-SF-neuroIC002},
typ = {PUB:(DE-HGF)24},
url = {https://juser.fz-juelich.de/record/910329},
}