The convergence speed is the most important feature of Back-Propagation (BP) algorithm. A lot of improvements were proposed to this algorithm since its presentation, in order to speed up the convergence phase. In this paper, a new modified BP algorithm called Speeding up Back-Propagation Learning (SUBPL) algorithm is proposed and compared to the standard BP. Different data sets were implemented and experimented to verify the improvement in SUBPL.

Association rules mining (ARM) is a fundamental and widely used data mining technique to achieve useful information about data. The traditional ARM algorithms are degrading computation efficiency by mining too many association rules which are not appropriate for a given user. Recent research in (ARM) is investigating the use of metaheuristic algorithms which are looking for only a subset of high-quality rules. In this paper, a modified discrete cuckoo search algorithm for association rules mining DCS-ARM is proposed for this purpose. The effectiveness of our algorithm is tested against a set of well-known transactional databases. Results indicate that the proposed algorithm outperforms the existing metaheuristic methods.

The first successful implementation of Artificial Neural Networks (ANNs) was published a little over a decade ago. It is time to review the progress that has been made in this research area. This paper provides taxonomy for classifying Field Programmable Gate Arrays (FPGAs) implementation of ANNs. Different implementation techniques and design issues are discussed, such as obtaining a suitable activation function and numerical truncation technique trade-off, the improvement of the learning algorithm to reduce the cost of neuron and in result the total cost and the total speed of the complete ANN. Finally, the implementation of a complete very fast circuit for the pattern of English Digit Numbers NN has four layers of 70 nodes (neurons) o

The first successful implementation of Artificial Neural Networks (ANNs) was published a little over a decade ago. It is time to review the progress that has been made in this research area. This paper provides taxonomy for classifying Field Programmable Gate Arrays (FPGAs) implementation of ANNs. Different implementation techniques and design issues are discussed, such as obtaining a suitable activation function and numerical truncation technique trade-off, the improvement of the learning algorithm to reduce the cost of neuron and in result the total cost and the total speed of the complete ANN. Finally, the implementation of a complete very fast circuit for the pattern of English Digit Numbers NN has four layers of 70 nodes (neurons) o

The Back-Propagation (BP) is the best known and widely used learning algorithm in training multiple neural network. A vast variety of improvements to BP algorithm have been proposed since ninety’s. in this paper, the effects of changing the number of hidden neurons and activation equation are investigated. According to the simulation results, the convergence speed have been improved and become much faster by the previous two modifications on the BP algorithm.

The issue of increasing the range covered by a wireless sensor network with restricted sensors is addressed utilizing improved CS employing the PSO algorithm and opposition-based learning (ICS-PSO-OBL). At first, the iteration is carried out by updating the old solution dimension by dimension to achieve independent updating across the dimensions in the high-dimensional optimization problem. The PSO operator is then incorporated to lessen the preference random walk stage's imbalance between exploration and exploitation ability. Exceptional individuals are selected from the population using OBL to boost the chance of finding the optimal solution based on the fitness value. The ICS-PSO-OBL is used to maximize coverage in WSN by converting r

In this paper, we derive and prove the stability bounds of the momentum coefficient µ and the learning rate ? of the back propagation updating rule in Artificial Neural Networks .The theoretical upper bound of learning rate ? is derived and its practical approximation is obtained

The study using Nonparametric methods for roubust to estimate a location and scatter it is depending  minimum covariance determinant of multivariate regression model , due to the presence of outliear values and increase the sample size and presence of more than after the model regression multivariate therefore be difficult to find a median location .       

It has been the use of genetic algorithm Fast – MCD – Nested Extension and compared with neural Network Back Propagation of multilayer in terms of accuracy of the results and speed in finding median location ,while the best sample to be determined by relying on less distance (Mahalanobis distance)has the stu

In this paper, two new simple, fast and efficient block matching algorithms are introduced, both methods begins blocks matching process from the image center block and moves across the blocks toward image boundaries. With each block, its motion vector is initialized using linear prediction that depending on the motion vectors of its neighbor blocks that are already scanned and their motion vectors are assessed. Also, a hybrid mechanism is introduced, it depends on mixing the proposed two predictive mechanisms with Exhaustive Search (ES) mechanism in order to gain matching accuracy near or similar to ES but with Search Time ST less than 80% of the ES. Also, it offers more control capability to reduce the search errors. The experimental tests

Face Identification is an important research topic in the field of computer vision and pattern recognition and has become a very active research area in recent decades. Recently multiwavelet-based neural networks (multiwavenets) have been used for function approximation and recognition, but to our best knowledge it has not been used for face Identification. This paper presents a novel approach for the Identification of human faces using Back-Propagation Adaptive Multiwavenet. The proposed multiwavenet has a structure similar to a multilayer perceptron (MLP) neural network with three layers, but the activation function of hidden layer is replaced with multiscaling functions. In experiments performed on the ORL face database it achieved a