% 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:916669,
author = {Fischer, Kirsten and Rene, Alexandre and Keup, Christian
and Layer, Moritz and Dahmen, David and Helias, Moritz},
title = {{D}ecomposing neural networks as mappings of correlation
functions},
reportid = {FZJ-2023-00020},
year = {2022},
abstract = {Understanding the functional principles of information
processing in deep neural networks continues to be a
challenge, in particular for networks with trained and thus
non-random weights. To address this issue, we study the
mapping between probability distributions implemented by a
deep feed-forward network. We characterize this mapping as
an iterated transformation of distributions, where the
non-linearity in each layer transfers information between
different orders of correlation functions. This allows us to
identify essential statistics in the data, as well as
different information representations that can be used by
neural networks. Applied to an XOR task and to MNIST, we
show that correlations up to second order predominantly
capture the information processing in the internal layers,
while the input layer also extracts higher-order
correlations from the data. This analysis provides a
quantitative and explainable perspective on classification.},
month = {Dec},
date = {2022-12-12},
organization = {Quantum Information Seminnar, Aachen
(Germany), 12 Dec 2022 - 12 Dec 2022},
subtyp = {Invited},
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)31},
url = {https://juser.fz-juelich.de/record/916669},
}