<div class="csl-bib-body">
<div class="csl-entry">Farsang, M., Neubauer, S., & Grosu, R. (2024, December 14). <i>Liquid Resistance Liquid Capacitance Networks</i> [Poster Presentation]. NeuroAI: Fusing Neuroscience and AI for Intelligent Solutions (NeuroAI @ NeurIPS2024), Canada.</div>
</div>
-
dc.identifier.uri
http://hdl.handle.net/20.500.12708/223289
-
dc.description.abstract
We introduce liquid-resistance liquid-capacitance neural networks (LRCs), a neural-ODE model which considerably improves the generalization, accuracy, and biological plausibility of electrical equivalent circuits (EECs), liquid time-constant networks (LTCs), and saturated liquid time-constant networks (STCs), respectively. We also introduce LRC units (LRCUs), as a very efficient and accurate gated RNN-model, which results from solving LRCs with an explicit Euler scheme using just one unfolding. We empirically show and formally prove that the liquid capacitance of LRCs considerably dampens the oscillations of LTCs and STCs, while at the same time dramatically increasing accuracy even for cheap solvers. We experimentally demonstrate that LRCs are a highly competitive alternative to popular neural ODEs and gated RNNs in terms of accuracy, efficiency, and interpretability, on classic time-series benchmarks and a complex autonomous-driving lane-keeping task.
en
dc.description.sponsorship
European Commission
-
dc.language.iso
en
-
dc.subject
bio-inspired model
en
dc.subject
recurrent neural network
en
dc.subject
neuron model
en
dc.subject
liquid
en
dc.title
Liquid Resistance Liquid Capacitance Networks
-
dc.type
Presentation
en
dc.type
Vortrag
de
dc.relation.grantno
101034277
-
dc.type.category
Poster Presentation
-
tuw.project.title
Technik für Biowissenschaften Doktoratsstudium
-
tuw.researchTopic.id
C5
-
tuw.researchTopic.id
C6
-
tuw.researchTopic.name
Computer Science Foundations
-
tuw.researchTopic.name
Modeling and Simulation
-
tuw.researchTopic.value
60
-
tuw.researchTopic.value
40
-
tuw.publication.orgunit
E191-01 - Forschungsbereich Cyber-Physical Systems
-
tuw.publication.orgunit
E056-17 - Fachbereich Trustworthy Autonomous Cyber-Physical Systems
-
tuw.author.orcid
0009-0002-9305-6507
-
tuw.author.orcid
0000-0001-5715-2142
-
tuw.event.name
NeuroAI: Fusing Neuroscience and AI for Intelligent Solutions (NeuroAI @ NeurIPS2024)
en
tuw.event.startdate
14-12-2024
-
tuw.event.enddate
14-12-2024
-
tuw.event.online
On Site
-
tuw.event.type
Event for scientific audience
-
tuw.event.country
CA
-
tuw.event.presenter
Farsang, Monika
-
wb.sciencebranch
Informatik
-
wb.sciencebranch
Elektrotechnik, Elektronik, Informationstechnik
-
wb.sciencebranch
Mathematik
-
wb.sciencebranch.oefos
1020
-
wb.sciencebranch.oefos
2020
-
wb.sciencebranch.oefos
1010
-
wb.sciencebranch.value
50
-
wb.sciencebranch.value
40
-
wb.sciencebranch.value
10
-
item.openairetype
conference poster not in proceedings
-
item.openairecristype
http://purl.org/coar/resource_type/c_18co
-
item.cerifentitytype
Publications
-
item.languageiso639-1
en
-
item.grantfulltext
none
-
item.fulltext
no Fulltext
-
crisitem.author.dept
E191-01 - Forschungsbereich Cyber-Physical Systems
-
crisitem.author.dept
E192-03 - Forschungsbereich Knowledge Based Systems
-
crisitem.author.dept
E191-01 - Forschungsbereich Cyber-Physical Systems
