An attractor-based complexity measurement for Boolean recurrent neural networks.
We provide a novel refined attractor-based complexity measurement for Boolean recurrent neural networks that represents an assessment of their computational power in terms of the significance of their attractor dynamics. This complexity measurement is achieved by first proving a computational equiva...
| Main Authors: | , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Public Library of Science (PLoS)
2014-01-01
|
| Series: | PLoS ONE |
| Online Access: | http://europepmc.org/articles/PMC3984152?pdf=render |
| _version_ | 1811209544681914368 |
|---|---|
| author | Jérémie Cabessa Alessandro E P Villa |
| author_facet | Jérémie Cabessa Alessandro E P Villa |
| author_sort | Jérémie Cabessa |
| collection | DOAJ |
| description | We provide a novel refined attractor-based complexity measurement for Boolean recurrent neural networks that represents an assessment of their computational power in terms of the significance of their attractor dynamics. This complexity measurement is achieved by first proving a computational equivalence between Boolean recurrent neural networks and some specific class of ω-automata, and then translating the most refined classification of ω-automata to the Boolean neural network context. As a result, a hierarchical classification of Boolean neural networks based on their attractive dynamics is obtained, thus providing a novel refined attractor-based complexity measurement for Boolean recurrent neural networks. These results provide new theoretical insights to the computational and dynamical capabilities of neural networks according to their attractive potentialities. An application of our findings is illustrated by the analysis of the dynamics of a simplified model of the basal ganglia-thalamocortical network simulated by a Boolean recurrent neural network. This example shows the significance of measuring network complexity, and how our results bear new founding elements for the understanding of the complexity of real brain circuits. |
| first_indexed | 2024-04-12T04:41:22Z |
| format | Article |
| id | doaj.art-88dbd8ba03804dd8945a49cf2d02c5a2 |
| institution | Directory Open Access Journal |
| issn | 1932-6203 |
| language | English |
| last_indexed | 2024-04-12T04:41:22Z |
| publishDate | 2014-01-01 |
| publisher | Public Library of Science (PLoS) |
| record_format | Article |
| series | PLoS ONE |
| spelling | doaj.art-88dbd8ba03804dd8945a49cf2d02c5a22022-12-22T03:47:39ZengPublic Library of Science (PLoS)PLoS ONE1932-62032014-01-0194e9420410.1371/journal.pone.0094204An attractor-based complexity measurement for Boolean recurrent neural networks.Jérémie CabessaAlessandro E P VillaWe provide a novel refined attractor-based complexity measurement for Boolean recurrent neural networks that represents an assessment of their computational power in terms of the significance of their attractor dynamics. This complexity measurement is achieved by first proving a computational equivalence between Boolean recurrent neural networks and some specific class of ω-automata, and then translating the most refined classification of ω-automata to the Boolean neural network context. As a result, a hierarchical classification of Boolean neural networks based on their attractive dynamics is obtained, thus providing a novel refined attractor-based complexity measurement for Boolean recurrent neural networks. These results provide new theoretical insights to the computational and dynamical capabilities of neural networks according to their attractive potentialities. An application of our findings is illustrated by the analysis of the dynamics of a simplified model of the basal ganglia-thalamocortical network simulated by a Boolean recurrent neural network. This example shows the significance of measuring network complexity, and how our results bear new founding elements for the understanding of the complexity of real brain circuits.http://europepmc.org/articles/PMC3984152?pdf=render |
| spellingShingle | Jérémie Cabessa Alessandro E P Villa An attractor-based complexity measurement for Boolean recurrent neural networks. PLoS ONE |
| title | An attractor-based complexity measurement for Boolean recurrent neural networks. |
| title_full | An attractor-based complexity measurement for Boolean recurrent neural networks. |
| title_fullStr | An attractor-based complexity measurement for Boolean recurrent neural networks. |
| title_full_unstemmed | An attractor-based complexity measurement for Boolean recurrent neural networks. |
| title_short | An attractor-based complexity measurement for Boolean recurrent neural networks. |
| title_sort | attractor based complexity measurement for boolean recurrent neural networks |
| url | http://europepmc.org/articles/PMC3984152?pdf=render |
| work_keys_str_mv | AT jeremiecabessa anattractorbasedcomplexitymeasurementforbooleanrecurrentneuralnetworks AT alessandroepvilla anattractorbasedcomplexitymeasurementforbooleanrecurrentneuralnetworks AT jeremiecabessa attractorbasedcomplexitymeasurementforbooleanrecurrentneuralnetworks AT alessandroepvilla attractorbasedcomplexitymeasurementforbooleanrecurrentneuralnetworks |