Types Of Training Algorithms Research Articles

Resource optimization of MIMO using neural network for 5G communication

The principal objective of this work is to optimize the resources of massive MIMO techniques by an application of a neural network algorithm in order to reduce the manufacturing cost of 5G technology within the wireless peripheries of tropical regions. For plenty of annual precipitation in the tropical regions, the radio signals of these areas get attenuated in communicating any message i.e. signal fading occurs. Various diversity techniques have been used for diminishing signal fading in these tropical areas. MIMO technique is a spatial diversity technique used to minimize signal fading. In this paper, 1 × 1 to 256 × 256 MIMO techniques have been designed with the help of MATLAB and Xilinx system generator, and an 8 × 8 MIMO has been implemented in Xilinx Kintex7 FPGA. A CMOS logic technique has been incorporated to optimize the resources of different MIMO techniques, and for this purpose a two-layer feed forward neural network algorithm has been adopted. A comparison of the theoretical values obtained from the design by using both Xilinx system generator and Simulink with the values derived from the design by using CMOS logic gates, has been displayed in this paper. For neural network optimization, three types of training algorithms have been applied.

Effect of Hidden Neuron Size on Different Training Algorithm in Neural Network

We use different types of training algorithms in the neural network. But, we cannot say which kind of training algorithm is fast for a given problem. So, in this survey paper, we are trying to find which types of training algorithm are better for categorization problems. For this purpose, we used ten types of training algorithms in the pattern network in MATLAB. We used Levenberg-Marquardt (LM), Bayesian regularization backpropagation (BR), BFGS Quasi-Newton (BFG), Resilient Backpropagation (RP), Scaled Conjugate gradient backpropagation (SCG), Conjugate Gradient with Powell/Beale Restarts (CGB), Fletcher-Powell Conjugate Gradient (CGF), Polak-Ribiere Conjugate Gradient (GDM), One Step Secant (OSS), and Variable Learning Rate Backpropagation (GD) algorithm. In this survey paper, we also check, affects of these algorithms on neural network when we applied different types of hidden neuron size. During this survey we found some new facts. We found that RP, SCG, CGB, CGF and OSS are fastest algorithms. BFG takes more time with respect to hidden neuron size. GDM and GD take more epochs. BR algorithm is not acceptable for image categorization.

Training of the feed forward artificial neural networks using dragonfly algorithm

One of the most important parts of an artificial neural network (ANN) which affects performance is training algorithms. Training algorithms optimize the weights and biases of the ANN according to the inputs–outputs pattern. Two types of training algorithms are widely used: Gradient methods and meta-heuristic methods. Gradient methods are effective in training the ANN. But they have some disadvantages. The main disadvantage of gradient methods is premature convergence. Secondly, the performance of gradient methods highly depends on the initial parameters and positions. Thirdly, they can easily get stuck in local optima. To overcome these disadvantages, this article presents a new hybrid algorithm (DA-MLP) to train the feed-forward multilayer neural networks (MLP) using the dragonfly algorithm. The dragonfly algorithm optimizes the weights and biases of the MLP. In the experiments, one real-world problem in the civil engineering area and eight classification datasets were used. To verify the success of the DA-MLP algorithm, the results of the DA-MLP algorithm were compared with the results of four algorithms (the BAT-MLP based on the bat optimization algorithm, the SMS-MLP based on the states of matter search optimization algorithm, the PSO-MLP based on the particle swarm optimization algorithm, and the backpropagation (BP) algorithm). The experimental study showed that the DA-MLP algorithm is more efficient than the other algorithms.

Performance Analysis of various Neural Network functions for Parkinson’s disease Classification using EEG and EMG

Artificial neural network (ANN) is a significant tool for classification of various types of disease using either Biosignals/images or may be any kind of physical parameters. Establishment of appropriate combination of learning, transfer function and training function is a very tedious task. Here, we compared the performance of different training parameters in feed forward neural network for differentiating of Parkinson’s disease using human brain (Electroencephalogram) and muscle signals (Electromyogram) features as the input vector. 3 different types of training algorithm with six training functions is used. They are Gradient Descent algorithms (traingd, traingdm), Conjugate Gradient algorithms (trainscg, traincgp) and Quasi-Newton algorithms (trainbfg, trainlm). Proposed work compared the mentioned algorithm in terms of mean square error, classification rate (%),R-value and the elapsed time. Study showed that trainlm (Levenberg-Marquardt) best fits for larger data set. It showed the highest accuracy rate of 100% with 0 mismatch classification with a best validation mean square error of 0.0040254 in 3 epochs with a elapsed time of 1.12 seconds. The R-value found was 0.9998 which is in nearly equals to 1. Hence, Levenberg-Marquardt can be used as a training function for the classification of any brain disorder

Electric power regulation and modeling of a central tower receiver power plant based on artificial neural network technique

This paper addresses an intelligent control scheme using the artificial neural network (ANN) technique for modeling and simulating a central tower receiver (CTR) plant with thermal energy storage (TES). The multilayer perceptron neural network (MLPNN) was implemented with two input parameters, one output parameter, and one hidden layer. The inputs comprise the receiver inlet temperature and the receiver thermal power. The output includes the mass flow rate of heat transfer fluid. A total of 888 datasets and three types of training algorithms, Levenberg-Marquardt (LM), Quasi-Newton, and Scaled Conjugate Gradient, are applied for training the proposed MLPNN model. Among all the investigated learning algorithms, the adopted LM with 40 neurons in the first hidden layer displayed superior ability to efficiently estimate the required performance compared to other learning algorithms. Based on the statistical evaluations, the optimized LM delivered preferred values for the root mean square error (0.0037), the coefficient of variance (0.0011), and the coefficient of determination (0.9999) during the training process. Hence, the MLPNN with LM-40 is an effective technique to precisely control the mass flow rate and subsequently the receiver outlet temperature regardless of the variations in the direct solar radiation and receiver inlet temperature. Furthermore, the generation strategy was modified to regulate CTR/TES output through electricity generation according to the hot storage system conditions. The performance of the adopted CTR-ANN model is presented and compared with the System Advisor Model (SAM) results. The results demonstrate better compatibility between the adopted CTR-ANN model and SAM outputs. The simplicity and minimum required input data of our proposed model make it appropriate for evaluating the power system reliability by using the Monte Carlo method.

An Artificial Neural Network for Analyzing Overall Uniformity in Outdoor Lighting Systems

Street lighting installations are an essential service for modern life due to their capability of creating a welcoming feeling at nighttime. Nevertheless, several studies have highlighted that it is possible to improve the quality of the light significantly improving the uniformity of the illuminance. The main difficulty arises when trying to improve some of the installation’s characteristics based only on statistical analysis of the light distribution. This paper presents a new algorithm that is able to obtain the overall illuminance uniformity in order to improve this sort of installations. To develop this algorithm it was necessary to perform a detailed study of all the elements which are part of street lighting installations. Because classification is one of the most important tasks in the application areas of artificial neural networks, we compared the performances of six types of training algorithms in a feed forward neural network for analyzing the overall uniformity in outdoor lighting systems. We found that the best algorithm that minimizes the error is “Levenberg-Marquardt back-propagation”, which approximates the desired output of the training pattern. By means of this kind of algorithm, it is possible to help to lighting professionals optimize the quality of street lighting installations.

Comparison of Neural Network Training Functions for Hematoma Classification in Brain CT Images

Classification is one of the most important task in application areas of artificial neural networks (ANN).Training neural networks is a complex task in the supervised learning field of research. The main difficulty in adopting ANN is to find the most appropriate combination of learning, transfer and training function for the classification task. We compared the performances of three types of training algorithms in feed forward neural network for brain hematoma classification. In this work we have selected Gradient Descent based backpropagation, Gradient Descent with momentum, Resilence backpropogation algorithms. Under conjugate based algorithms, Scaled Conjugate back propagation, Conjugate Gradient backpropagation with Polak-Riebreupdates(CGP) and Conjugate Gradient backpropagation with Fletcher-Reeves updates (CGF).The last category is Quasi Newton based algorithm, under this BFGS, Levenberg-Marquardt algorithms are selected. Proposed work compared training algorithm on the basis of mean square error, accuracy, rate of convergence and correctness of the classification. Our conclusion about the training functions is based on the simulation results.

Assessment of the performances of multilayer perceptron neural networks in comparison with recurrent neural networks and two statistical methods for diagnosing coronary artery disease

Abstract: We aimed to examine the diagnostic performances of multilayer perceptron neural networks (MLPNNs) for predicting coronary artery disease and to compare them with different types of artificial neural network methods, namely recurrent neural networks (RNNs) and two statistical methods (quadratic discriminant analysis (QDA) and logistic regression (LR)). MLPNNs were trained with backpropagation, quick propagation, delta‐bar‐delta and extended delta‐bar‐delta algorithms as classifiers; the RNN was trained with the Levenberg–Marquardt algorithm; LR and QDA were used for predicting coronary artery disease. Coronary artery disease was classified with accuracy rates varying from 79.9% to 83.9% by MLPNNs. Even though MLPNNs achieved higher accuracy rates than the statistical methods, LR (73.2%) and QDA (58.4%), their performances were lower compared to the RNN (84.7%). Among the four different types of training algorithms that trained MLPNNs, quick propagation achieved the highest accuracy rate; however, it was lower than the RNN trained with the Levenberg–Marquardt algorithm. RNNs, which demonstrated 84.7% accuracy and 86.5% positive predictive rates, may be a helpful tool in medical decision making for diagnosis of coronary artery disease.