<div class="csl-bib-body">
<div class="csl-entry">Hasani, R., Lechner, M., Amini, A., Rus, D., & Grosu, R. (2020). The Natural Lottery Ticket Winner: Reinforcement Learning with Ordinary Neural Circuits. In <i>Proceedings of the 37th International Conference on Machine Learning (ICML 2020), Vienna, Austria, PMLR 119, 2020</i>. https://doi.org/10.34726/241</div>
</div>
-
dc.identifier.uri
http://hdl.handle.net/20.500.12708/15629
-
dc.identifier.uri
https://doi.org/10.34726/241
-
dc.description.abstract
We propose a neural information processing system which is obtained by re-purposing the function of a biological neural circuit model to govern simulated and real-world control tasks. Inspired by the structure of the nervous system of the soil-worm, C. elegans, we introduce ordinary neural circuits (ONCs), defined as the model of biological neural circuits reparameterized for the control of alternative tasks. We first demonstrate that ONCs realize networks with higher maximum flow compared to arbitrary wired networks. We then learn instances of ONCs to control a series of robotic tasks, including the autonomous parking of a real-world rover robot. For reconfiguration of the purpose of the neural circuit, we adopt a search-based optimization algorithm. Ordinary neural circuits perform on par and, in some cases, significantly surpass the performance of contemporary deep learning models. ONC networks are compact, 77% sparser than their counterpart neural controllers, and their neural dynamics are fully interpretable at the cell-level.
en
dc.description.sponsorship
RH and RG are partially supported by Horizon-2020 ECSEL Project grant No. 783163 (iDev40), Productive 4.0, and ATBMBFW CPS-IoT Ecosystem. ML was supported in part by the Austrian Science Fund (FWF) under grant Z211-N23 (Wittgenstein Award). AA is supported by the National Science Foundation (NSF) Graduate Research Fellowship Program. RH and DR are partially supported by The Boeing Company and JP Morgan Chase. This research work is partially drawn from the PhD dissertation of RH.
-
dc.language.iso
en
-
dc.rights.uri
http://rightsstatements.org/vocab/InC/1.0/
-
dc.subject
Deep Learning
en
dc.subject
Machine Learning
en
dc.subject
Artificial Intelligence
en
dc.subject
biological neural networks
en
dc.subject
Robotics
en
dc.subject
Reinforcement learning
en
dc.subject
interpretable AI
en
dc.title
The Natural Lottery Ticket Winner: Reinforcement Learning with Ordinary Neural Circuits
en
dc.type
Inproceedings
en
dc.type
Konferenzbeitrag
de
dc.rights.license
Urheberrechtsschutz
de
dc.rights.license
In Copyright
en
dc.identifier.doi
10.34726/241
-
dc.contributor.affiliation
Massachusetts Institute of Technology, USA
-
dc.contributor.affiliation
Massachusetts Institute of Technology, USA
-
dc.type.category
Full-Paper Contribution
-
tuw.booktitle
Proceedings of the 37th International Conference on Machine Learning (ICML 2020), Vienna, Austria, PMLR 119, 2020