% 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{Weidel:890994,
author = {Weidel, Philipp and Duarte, Renato and Morrison, Abigail},
title = {{U}nsupervised {L}earning and {C}lustered {C}onnectivity
{E}nhance {R}einforcement {L}earning in {S}piking {N}eural
{N}etworks},
journal = {Frontiers in computational neuroscience},
volume = {15},
issn = {1662-5188},
address = {Lausanne},
publisher = {Frontiers Research Foundation},
reportid = {FZJ-2021-01301},
pages = {543872},
year = {2021},
abstract = {Reinforcement learning is a paradigm that can account for
how organisms learn to adapt their behavior in complex
environments with sparse rewards. To partition an
environment into discrete states, implementations in spiking
neuronal networks typically rely on input architectures
involving place cells or receptive fields specified ad hoc
by the researcher. This is problematic as a model for how an
organism can learn appropriate behavioral sequences in
unknown environments, as it fails to account for the
unsupervised and self-organized nature of the required
representations. Additionally, this approach presupposes
knowledge on the part of the researcher on how the
environment should be partitioned and represented and scales
poorly with the size or complexity of the environment. To
address these issues and gain insights into how the brain
generates its own task-relevant mappings, we propose a
learning architecture that combines unsupervised learning on
the input projections with biologically motivated clustered
connectivity within the representation layer. This
combination allows input features to be mapped to clusters;
thus the network self-organizes to produce clearly
distinguishable activity patterns that can serve as the
basis for reinforcement learning on the output projections.
On the basis of the MNIST and Mountain Car tasks, we show
that our proposed model performs better than either a
comparable unclustered network or a clustered network with
static input projections. We conclude that the combination
of unsupervised learning and clustered connectivity provides
a generic representational substrate suitable for further
computation.},
cin = {INM-6 / IAS-6 / INM-10 / JARA-HPC},
ddc = {610},
cid = {I:(DE-Juel1)INM-6-20090406 / I:(DE-Juel1)IAS-6-20130828 /
I:(DE-Juel1)INM-10-20170113 / $I:(DE-82)080012_20140620$},
pnm = {523 - Neuromorphic Computing and Network Dynamics
(POF4-523) / 89574 - Theory, modelling and simulation
(POF2-89574) / Functional Neural Architectures
$(jinm60_20190501)$ / 5232 - Computational Principles
(POF4-523)},
pid = {G:(DE-HGF)POF4-523 / G:(DE-HGF)POF2-89574 /
$G:(DE-Juel1)jinm60_20190501$ / G:(DE-HGF)POF4-5232},
typ = {PUB:(DE-HGF)16},
pubmed = {33746728},
UT = {WOS:000629977000001},
doi = {10.3389/fncom.2021.543872},
url = {https://juser.fz-juelich.de/record/890994},
}