Charting epilepsy by searching for intelligence in network space with the help of evolving autonomous agents

The problem of demarcating neural network space is formidable. A simple fully connected recurrent network of five units (binary activations, synaptic weight resolution of 10) has 3.2 ∗ 10 26 possible initial states. The problem increases drastically with scaling. Here we consider three complementary...

Ausführliche Beschreibung

Gespeichert in:

Bibliographische Detailangaben
Veröffentlicht in:	Journal of physiology, Paris Paris, 2004-07, Vol.98 (4), p.507-529
Hauptverfasser:	Ohayon, Elan L., Kalitzin, Stiliyan, Suffczynski, Piotr, Jin, Frank Y., Tsang, Paul W., Borrett, Donald S., Burnham, W. McIntyre, Kwan, Hon C.
Format:	Artikel
Sprache:	eng
Schlagworte:	Action Potentials - physiology Algorithms Animals Artificial life Autism Biological Clocks - physiology Brain Mapping - methods Close return Computer modeling Computer Simulation Epilepsy - physiopathology Epilepsy - therapy Genetic algorithm Graph theory Humans Mathematics Models, Neurological Motor Neurons - physiology Nerve Net - physiopathology Neural Networks (Computer) Neuronal Plasticity - physiology Recurrent neural network Robot Robotics Seizures Self-organization Synchrony
Online-Zugang:	Volltext
Tags:	Tag hinzufügen Keine Tags, Fügen Sie den ersten Tag hinzu!

Schreiben Sie den ersten Kommentar!