Abstract Machine learning algorithms can study existing data to perform specific tasks. One of the well-known machine is backpropagation algorithm, but this algorithm often provides poor convergence speed in training process and a long time. The purpose optimize standard using Beale-Powell conjugate gradient so that time needed achieve not too long, which later be used as reference information ...

A Bayesian regularization-backpropagation neural network (BR-BPNN) model is employed to predict some aspects of the gecko spatula peeling, viz. variation maximum normal and tangential pull-off forces resultant force angle at detachment with peeling angle. K-fold cross validation used improve effectiveness model. The input data taken from finite element (FE) results. trained 75% FE dataset. rema...

Solving real world problems with embedded neural networks requires both training algorithms that achieve high performance and compatible hardware that runs in real time while remaining energy efficient. For the former, deep learning using backpropagation has recently achieved a string of successes across many domains and datasets. For the latter, neuromorphic chips that run spiking neural netwo...

This paper proposes a technique for recognizing Arabic characters. This technique involves of three parts: body classifier, complementary classifier, and aggregate classifier. The body classifier is designed to recognize the main body of the unknown character. It uses a Hopfield network to enhance the unknown character and to get rid of noise and associated complementary. Furthermore, it uses a...

Providing credit has become a main source of profit for financial and non-financial institutions. However, this transaction might lead into risk. This risk occurred if debtors unable to complete their obligations that will led loss creditors. It is necessity company create assessment in distinguishing eligible or non-eligible prospective customer. Artificial Neural Network (ANN) introduced solv...

This paper presents experimental results of an original approach to the Neural Network learning architecture for the control and the adaptive control of mobile robots. The basic idea is to use non-recurrent multi-layer-network and the backpropagation algorithm without desired outputs, but with a quadratic criterion which spezify the control objective. To illustrate this method, we consider an e...

This section introduces multilayer perceptrons, which are the most commonly used type of neural network. The popular backpropagation training algorithm is studied in detail. The momentum and adaptive step size techniques, which are used for accelerated training, are discussed. Other acceleration techniques are briefly referenced. Several implementation issues are then examined. The issue of gen...