Displaying similar documents to “Solving maximum independent set by asynchronous distributed hopfield-type neural networks”

Hybrid Particle Swarm and Neural Network Approach for Streamflow Forecasting

A. Sedki, D. Ouazar (2010)

Mathematical Modelling of Natural Phenomena

Similarity:

In this paper, an artificial neural network (ANN) based on hybrid algorithm combining particle swarm optimization (PSO) with back-propagation (BP) is proposed to forecast the daily streamflows in a catchment located in a semi-arid region in Morocco. The PSO algorithm has a rapid convergence during the initial stages of a global search, while the BP algorithm can achieve faster convergent speed around the global optimum. By combining the...

An Adaptation of the Hoshen-Kopelman Cluster Counting Algorithm for Honeycomb Networks

Popova, Hristina (2014)

Serdica Journal of Computing

Similarity:

We develop a simplified implementation of the Hoshen-Kopelman cluster counting algorithm adapted for honeycomb networks. In our implementation of the algorithm we assume that all nodes in the network are occupied and links between nodes can be intact or broken. The algorithm counts how many clusters there are in the network and determines which nodes belong to each cluster. The network information is stored into two sets of data. The first one is related to the connectivity of the...

Ant algorithm for flow assignment in connection-oriented networks

Krzysztof Walkowiak (2005)

International Journal of Applied Mathematics and Computer Science

Similarity:

This work introduces ANB (bf Ant Algorithm for bf Non-bf Bifurcated Flows), a novel approach to capacitated static optimization of flows in connection-oriented computer networks. The problem considered arises naturally from several optimization problems that have recently received significant attention. The proposed ANB is an ant algorithm motivated by recent works on the application of the ant algorithm to solving various problems related to computer networks. However, few works concern...

The UD RLS algorithm for training feedforward neural networks

Jarosław Bilski (2005)

International Journal of Applied Mathematics and Computer Science

Similarity:

A new algorithm for training feedforward multilayer neural networks is proposed. It is based on recursive least squares procedures and U-D factorization, which is a well-known technique in filter theory. It will be shown that due to the U-D factorization method, our algorithm requires fewer computations than the classical RLS applied to feedforward multilayer neural network training.