Fault Tolerance for Small-World Cellular Neural Networks

2008 ◽  
pp. 223-231 ◽  
Author(s):  
Kautsuyoshi Matsumoto ◽  
Minoru Uehara ◽  
Hideki Mori
Keyword(s):  
Neural Networks ◽  
Fault Tolerance ◽  
Small World ◽  
Cellular Neural Networks

CELLULAR NEURAL NETWORKS CAN MIMIC SMALL-WORLD NETWORKS

1999 ◽  
Vol 09 (10) ◽  
pp. 2105-2126 ◽  
Author(s):  
TAO YANG ◽  
LEON O. CHUA
Keyword(s):  
Neural Networks ◽  
Coupling Strength ◽  
Initial Conditions ◽  
Computing Time ◽  
Small World ◽  
Cellular Neural Networks ◽  
Clustering Coefficient ◽  
High Survival ◽  
Game Of Life ◽  
Hole Detection

Small-world phenomenon can occur in coupled dynamical systems which are highly clustered at a local level and yet strongly coupled at the global level. We show that cellular neural networks (CNN's) can exhibit "small-world phenomenon". We generalize the "characteristic path length" from previous works on "small-world phenomenon" into a "characteristic coupling strength" for measuring the average coupling strength of the outputs of CNN's. We also provide a simplified algorithm for calculating the "characteristic coupling strength" with a reasonable amount of computing time. We define a "clustering coefficient" and show how it can be calculated by a horizontal "hole detection" CNN, followed by a vertical "hole detection" CNN. Evolutions of the game-of-life CNN with different initial conditions are used to illustrate the emergence of a "small-world phenomenon". Our results show that the well-known game-of-life CNN is not a small-world network. However, generalized CNN life games whose individuals have strong mobility and high survival rate can exhibit small-world phenomenon in a robust way. Our simulations confirm the conjecture that a population with a strong mobility is more likely to qualify as a small world. CNN games whose individuals have weak mobility can also exhibit a small-world phenomenon under a proper choice of initial conditions. However, the resulting small worlds depend strongly on the initial conditions, and are therefore not robust.

A New Small-World Neural Network with its Performance on Fault Tolerance

2012 ◽  
Vol 629 ◽  
pp. 719-724
Author(s):  
Xiao Hu Li ◽  
Feng Xu ◽  
Jin Hua Zhang ◽  
Su Nan Wang
Keyword(s):  
Neural Network ◽  
Neural Networks ◽  
Fault Tolerance ◽  
Random Network ◽  
Small World ◽  
Simple Simulation ◽  
Neuron Damage ◽  
Regular Network ◽  
Artificial Neural ◽  
And Function

Many artificial neural networks are the simple simulation of brain neural network’s architecture and function. However, how to rebuild new artificial neural network which architecture is similar to biological neural networks is worth studying. In this study, a new multilayer feedforward small-world neural network is presented using the results form research on complex network. Firstly, a new multilayer feedforward small-world neural network which relies on the rewiring probability heavily is built up on the basis of the construction ideology of Watts-Strogatz networks model and community structure. Secondly, fault tolerance is employed in investigating the performances of new small-world neural network. When the network with connection fault or neuron damage is used to test the fault tolerance performance under different rewiring probability, simulation results show that the fault tolerance capability of small-world neural network outmatches that of the same scale regular network when the fault probability is more than 40%, while random network has the best fault tolerance capability.

Sign in / Sign up

Export Citation Format

Share Document