Performance comparison of ANN training algorithms for classification

Baptista, F. Dario; Rodrigues, Sandy; Morgado‐Dias, Fernando

doi:10.1109/wisp.2013.6657493

Cited by 22 publications

(17 citation statements)

References 3 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The feed forward neural network is built using of Levenberg-Marquardt training algorithm which is widely used in classification literature [14,15,16].The network architecture used is composed of nine neurons for input layer and one neuron for the output layer. To achieve the paper objectives, www.ijacsa.thesai.org the number of hidden layers and the number of neurons per hidden layer are changed during the training and simulation of the network.…”

Section: Methodsmentioning

confidence: 99%

Determining the Efficient Structure of Feed-Forward Neural Network to Classify Breast Cancer Dataset

Ahmed¹,

Noureldien²

2014

ijacsa

View full text Add to dashboard Cite

Abstract-Classification is one of the most frequently encountered problems in data mining. A classification problem occurs when an object needs to be assigned in predefined classes based on a number of observed attributes related to that object.Neural networks have emerged as one of the tools that can handle the classification problem. Feed-forward Neural Networks (FNN's) have been widely applied in many different fields as a classification tool.Designing an efficient FNN structure with optimum number of hidden layers and minimum number of layer's neurons, given a specific application or dataset, is an open research problem.In this paper, experimental work is carried out to determine an efficient FNN structure, that is, a structure with the minimum number of hidden layer's neurons for classifying the Wisconsin Breast Cancer Dataset. We achieve this by measuring the classification performance using the Mean Square Error (MSE) and controlling the number of hidden layers, and the number of neurons in each layer.The experimental results show that the number of hidden layers has a significant effect on the classification performance and the best classification performance average is attained when the number of layers is 5, and number of hidden layer's neurons are small, typically 1 or 2.

show abstract

Section: Methodsmentioning

confidence: 99%

Determining the Efficient Structure of Feed-Forward Neural Network to Classify Breast Cancer Dataset

Ahmed¹,

Noureldien²

2014

ijacsa

View full text Add to dashboard Cite

show abstract

“…There are several training algorithms for training the neural network weights, the most important being the backpropagation (BP) algorithm, in which the output error starts from the output layer and propagates backwards until it reaches the hidden layer next to the input layer to update the weights. Based on the update strategy, there are different variations of BP, the most common being BP based on gradient descent (GD) [20]. With reference to Figure 1, the GD-based BP algorithm for updating the weights can be summarized by the following equations, assuming a linear activation function for the output layer and nonlinear activation functions for the hidden layers.…”

Section: The DL Controllermentioning

confidence: 99%

Deep Learning Control for Digital Feedback Systems: Improved Performance with Robustness against Parameter Change

Alwan

Hussain

2021

Electronics

View full text Add to dashboard Cite

Training data for a deep learning (DL) neural network (NN) controller are obtained from the input and output signals of a conventional digital controller that is designed to provide the suitable control signal to a specified plant within a feedback digital control system. It is found that if the DL controller is sufficiently deep (four hidden layers), it can outperform the conventional controller in terms of settling time of the system output transient response to a unit-step reference signal. That is, the DL controller introduces a damping effect. Moreover, it does not need to be retrained to operate with a reference signal of different magnitude, or under system parameter change. Such properties make the DL control more attractive for applications that may undergo parameter variation, such as sensor networks. The promising results of robustness against parameter changes are calling for future research in the direction of robust DL control.

show abstract

“…A backpropagation strategy is used to optimize the NN performance. Scaled conjugate gradient backpropagation (trainscg) is one of the most commonly applied functions with NN and has produced efficient results [27]. Therefore, this technique is selected to be the learning function of the design.…”

Section: Proposed Ensemble Designmentioning

confidence: 99%

Automated Glioma Grading based on an Efficient Ensemble Design of a Multiple Classifier System using Deep Iteration Neural Networks Matrix

Al-Zurfi

Meziane

Aspin

2018

2018 24th International Conference on Automation and Computing (ICAC)

View full text Add to dashboard Cite

the preoperative diagnosis of brain Glioma grades is crucial for therapeutic planning as it impacts on the tumour's prognosis. The development of machine learning methods that can accurately evaluate Glioma grades is of great interest since it is a repeatable and reliable diagnosis procedure. Moreover, the classification accuracy of a single classifier can be further improved by using the ensemble of different classifiers. In this paper, a new strategy has been developed, which uses a deep neural network incorporating an extensive iteration matrix based on the combination of eleven different machine learning algorithms. The classification system is evaluated using a crossvalidation technique, to add more generalization to the results of the classification system's reliability in unseen cases. Experimental results indicate that, when compared to both the single classification model, and the majority vote scheme, the grading accuracy has significantly improved using our proposed approach. The obtained sensitivity, specificity and accuracy are 100%, 90% and 93.3% respectively. The proposed approach has improved upon the highest accuracy of the single classification model by 13.3%. The proposed classification system presents an efficient method to evaluate the malignancy level of Glioma with more reliable and accurate clinical outcomes.

show abstract

Performance comparison of ANN training algorithms for classification

Cited by 22 publications

References 3 publications

Determining the Efficient Structure of Feed-Forward Neural Network to Classify Breast Cancer Dataset

Determining the Efficient Structure of Feed-Forward Neural Network to Classify Breast Cancer Dataset

Deep Learning Control for Digital Feedback Systems: Improved Performance with Robustness against Parameter Change

Automated Glioma Grading based on an Efficient Ensemble Design of a Multiple Classifier System using Deep Iteration Neural Networks Matrix

Contact Info

Product

Resources

About