CoDi: Difference between revisions
Marking as reviewing |
Changing raw references into citations |
||
Line 3: | Line 3: | ||
[[File:CoDi_CA_signaling.png|100px|right|Codi signaling]] |
[[File:CoDi_CA_signaling.png|100px|right|Codi signaling]] |
||
CoDi is a cellular [[Cellular automaton|automaton/automata (CA)]] model for |
'''CoDi''' is a cellular [[Cellular automaton|automaton/automata (CA)]] model for [[Spiking neural network|spiking neural networks (SNNs)]]. CoDi is an acronym for Collect and Distribute referring to the signals/spikes in a neural network. |
||
[[Spiking neural network|spiking neural networks (SNNs)]]. |
|||
DoDi stands for Collect and Distribute referring to the signals/spikes in a neural network. |
|||
==General Description and Rules of the CoDi CA== |
==General Description and Rules of the CoDi CA== |
||
Line 11: | Line 9: | ||
[[File:CoDi_CA_signaling_rules.png|250px|right|Codi signaling rules]] |
[[File:CoDi_CA_signaling_rules.png|250px|right|Codi signaling rules]] |
||
CoDi uses a von Neumann neighborhood, in a 3D space, thus it looks at 6 neighbors and at its own state. In a growth phase a neural network is grows in the CA-space based on an underlying chromosome. There are only 3 types of cells: neuron body, axon, dendrite and blank. The growth phase is followed by a signaling- or processing-phase.Signals are distributed from the neuron bodies vie their axons tree and collected from connection dendrites. |
|||
CoDi uses a von Neumann neighborhood, |
|||
in a 3D space, thus it looks at |
|||
6 neighbors and at its own state. |
|||
In a growth phase a neural network is grows in the CA-space based on an underlying chromosome. |
|||
There are only 3 types of cells: neuron body, axon, dendrite and blank. |
|||
The growth phase is followed by a signaling- or processing-phase. |
|||
Signals are distributed from the neuron bodies vie their axons tree and collected |
|||
from connection dendrites. |
|||
==History== |
==History== |
||
CoDi was introduced by Gers et. al. <ref name="Gers1998">{{cite journal|last=Gers|first=Felix|coauthors=Hugo Garis, Michael Korkin|year=1998|title=CoDi-1Bit : A simplified cellular automata based neuron model|volume=1363|pages=315–333|doi=10.1007/BFb0026610}}</ref>. |
|||
CoDi was introduced by Gers et. al. |
|||
<ref>F.A. Gers, H. De Garis and M. Korkin, [http://felixgers.de/papers/codi-1bit.pdf "Codi-1bit : A simplified cellular automata based neuron model"], ''In Artificial Evolution Conference (AE), Nimes, France'', 1997.</ref>. |
|||
A specialized parallel machine based on FPGA Hardware to run the DoDi model on a large scale was developed by Korkin et. al. |
A specialized parallel machine based on FPGA Hardware to run the DoDi model on a large scale was developed by Korkin et. al. |
||
<ref name="de Garis2001">{{cite journal|last=de Garis|first=Hugo|coauthors=Michael Korkin, Gary Fehr|year=2001|journal=Autonomous Robots|volume=10|issue=3|pages=235–249|issn=09295593|doi=10.1023/A:1011286308522}}</ref>. |
|||
<ref>M. Korkin, H. De Garis, F. A. Gers, and H. Hemmi, "CBM (CAM-brain machine) : A hardware tool which evolves a neural net module in a fraction of a second and runs a million neuron artificial brain in real time", In Genetic Programming Conference, Stanford, USA, 1997.</ref>. |
|||
The original model, where learning is based on evolutionary algorithms, has been augmented with a local learning rule via feedback from dendritic spikes by Schwarzer |
The original model, where learning is based on evolutionary algorithms, has been augmented with a local learning rule via feedback from dendritic spikes by Schwarzer |
||
<ref name=" |
<ref name="SchwarzerMüller-Schloer2004">{{cite book|last1=Schwarzer|first1=Jens|last2=Müller-Schloer|first2=Christian|title=Lernverfahren für evolutionär optimierte Künstliche Neuronale Netze auf der Basis Zellulärer Automaten|url=http://books.google.com/books?id=wVuqAAAACAAJ|accessdate=7 January 2013|date=2004-08-05|publisher=Logos Verlag Berlin|isbn=9783832506285|pages=125–}}</ref>. |
||
==References== |
==References== |
Revision as of 20:07, 7 January 2013
This article, CoDi, has recently been created via the Articles for creation process. Please check to see if the reviewer has accidentally left this template after accepting the draft and take appropriate action as necessary.
Reviewer tools: Inform author |
CoDi is a cellular automaton/automata (CA) model for spiking neural networks (SNNs). CoDi is an acronym for Collect and Distribute referring to the signals/spikes in a neural network.
General Description and Rules of the CoDi CA
CoDi uses a von Neumann neighborhood, in a 3D space, thus it looks at 6 neighbors and at its own state. In a growth phase a neural network is grows in the CA-space based on an underlying chromosome. There are only 3 types of cells: neuron body, axon, dendrite and blank. The growth phase is followed by a signaling- or processing-phase.Signals are distributed from the neuron bodies vie their axons tree and collected from connection dendrites.
History
CoDi was introduced by Gers et. al. [1]. A specialized parallel machine based on FPGA Hardware to run the DoDi model on a large scale was developed by Korkin et. al. [2]. The original model, where learning is based on evolutionary algorithms, has been augmented with a local learning rule via feedback from dendritic spikes by Schwarzer [3].
References
- ^ Gers, Felix (1998). "CoDi-1Bit : A simplified cellular automata based neuron model". 1363: 315–333. doi:10.1007/BFb0026610.
{{cite journal}}
: Cite journal requires|journal=
(help); Unknown parameter|coauthors=
ignored (|author=
suggested) (help) - ^ de Garis, Hugo (2001). Autonomous Robots. 10 (3): 235–249. doi:10.1023/A:1011286308522. ISSN 0929-5593.
{{cite journal}}
: Missing or empty|title=
(help); Unknown parameter|coauthors=
ignored (|author=
suggested) (help) - ^ Schwarzer, Jens; Müller-Schloer, Christian (2004-08-05). Lernverfahren für evolutionär optimierte Künstliche Neuronale Netze auf der Basis Zellulärer Automaten. Logos Verlag Berlin. pp. 125–. ISBN 9783832506285. Retrieved 7 January 2013.