Self-Organized Neural Networks

2000 ◽  
pp. 177-195
Author(s):  
Xiang-Sun Zhang
Keyword(s):  
Neural Networks ◽  
Self Organized

scholarly journals Self-organized Operational Neural Networks with generative neurons

2021 ◽  
Author(s):  
Serkan Kiranyaz ◽  
Junaid Malik ◽  
Habib Ben Abdallah ◽  
Turker Ince ◽  
Alexandros Iosifidis ◽  
...  
Keyword(s):  
Neural Networks ◽  
Self Organized

scholarly journals Analytical investigation of self-organized criticality in neural networks

2013 ◽  
Vol 10 (78) ◽  
pp. 20120558 ◽  
Author(s):  
Felix Droste ◽  
Anne-Ly Do ◽  
Thilo Gross
Keyword(s):  
Neural Networks ◽  
Stochastic Dynamics ◽  
Analytical Investigation ◽  
Homeostatic Plasticity ◽  
Dynamical Phase Transition ◽  
Discrete State ◽  
Dynamical Phase ◽  
Self Organized ◽  
Self Organized Criticality ◽  
Activity Dependent

Dynamical criticality has been shown to enhance information processing in dynamical systems, and there is evidence for self-organized criticality in neural networks. A plausible mechanism for such self-organization is activity-dependent synaptic plasticity. Here, we model neurons as discrete-state nodes on an adaptive network following stochastic dynamics. At a threshold connectivity, this system undergoes a dynamical phase transition at which persistent activity sets in. In a low-dimensional representation of the macroscopic dynamics, this corresponds to a transcritical bifurcation. We show analytically that adding activity-dependent rewiring rules, inspired by homeostatic plasticity, leads to the emergence of an attractive steady state at criticality and present numerical evidence for the system's evolution to such a state.

scholarly journals Intrinsic Adaptation in Autonomous Recurrent Neural Networks

2012 ◽  
Vol 24 (2) ◽  
pp. 523-540 ◽  
Author(s):  
Dimitrije Marković ◽  
Claudius Gros
Keyword(s):  
Neural Networks ◽  
Information Processing ◽  
Neural Activity ◽  
Recurrent Neural Networks ◽  
Activity Patterns ◽  
Self Organized ◽  
Dynamical Regimes ◽  
Autonomous State ◽  
Adaptation Processes ◽  
External Stimuli

A massively recurrent neural network responds on one side to input stimuli and is autonomously active, on the other side, in the absence of sensory inputs. Stimuli and information processing depend crucially on the qualia of the autonomous-state dynamics of the ongoing neural activity. This default neural activity may be dynamically structured in time and space, showing regular, synchronized, bursting, or chaotic activity patterns. We study the influence of nonsynaptic plasticity on the default dynamical state of recurrent neural networks. The nonsynaptic adaption considered acts on intrinsic neural parameters, such as the threshold and the gain, and is driven by the optimization of the information entropy. We observe, in the presence of the intrinsic adaptation processes, three distinct and globally attracting dynamical regimes: a regular synchronized, an overall chaotic, and an intermittent bursting regime. The intermittent bursting regime is characterized by intervals of regular flows, which are quite insensitive to external stimuli, interceded by chaotic bursts that respond sensitively to input signals. We discuss these findings in the context of self-organized information processing and critical brain dynamics.

Sign in / Sign up

Export Citation Format

Share Document