Sign inSubmit
Tips: “quotes” for a phrase · author:Lee · a DOI goes straight to its article

139 results for “Training Algorithm”
Set a search alert
Research ArticleOpen accessIn the abstractAn Efficient and Effective Immune Based ClassifierShahram Golzari, Shyamala Doraisamy, Md Nasir Sulaiman, Nur Izura UdzirProblem statement: Artificial Immune Recognition System (AIRS) is most popular and effective immune inspired classifier. Resource competition is one stage of AIRS. Resource competition is done based on the number of allocated resources. AIRS uses a linear method to allocate resources. The linear resource allocation increases the training time of classifier. Approach: In this study, a new nonlinear resource allocation … …Journal of Computer Science, Vol. 7, Issue 2 · 25 Feb 2011 · 7,768 accessesView PDFCite
Research ArticleOpen accessIn the abstractAdaptive Resonance Theory Training Parameters: Pretty Good SetsTaisir Mohammad Eldos, Abdulaziz Suleiman AlmazyadProblem statement: ART1 artificial neural networks offer good tools for test clustering, where no expert is needed if the system is well trained. However, having no output reference for the input patterns makes it hard to judge the quality of the training. Moreover, the performance depends to a great extent on a set of training parameters. Designers follow some recommendations … …Journal of Computer Science, Vol. 6, Issue 12 · 6 Nov 2010 · 7,155 accessesView PDFCite
Research ArticleOpen accessIn the abstractNeural Network Change Detection Model for Satellite Images Using Textural and Spectral CharacteristicsA. K. Helmy, Gh. S. El-TaweelProblem statement: Change detection is the process of identifying difference of the state of an object or phenomena by observing it at different time. Essentially, it involves the ability to quantify temporal effects using multi-temporal data sets. Information about change is necessary for evaluating land cover and the management of natural resources. Approach: A neural network model based on both … …American Journal of Engineering and Applied Sciences, Vol. 3, Issue 4 · 4 Nov 2010 · 8,156 accessesView PDFCite
Research ArticleOpen accessIn the abstractImproving the Performance of Backpropagation Neural Network Algorithm for Image Compression/Decompression SystemOmaima N.A. AL-AllafProblem statement: The problem inherent to any digital image is the large amount of bandwidth required for transmission or storage. This has driven the research area of image compression to develop algorithms that compress images to lower data rates with better quality. Artificial neural networks are becoming attractive in image processing where high computational performance and parallel architectures are required. … …Journal of Computer Science, Vol. 6, Issue 11 · 26 Oct 2010 · 8,370 accessesView PDFCite
Research ArticleOpen accessIn the abstractA Derivative-Free Optimization Method for Solving Classification ProblemParvaneh Shabanzadeh, Malik Abu Hassan, Wah June LeongProblem statement: The aim of data classification is to establish rules for the classification of some observations assuming that we have a database, which includes of at least two classes. There is a training set for each class. Those problems occur in a wide range of human activity. One of the most promising ways to data classification is based on … …Journal of Computer Science, Vol. 6, Issue 3 · 31 Mar 2010 · 7,505 accessesView PDFCite
Research ArticleOpen accessIn the abstractA Modified Conjugate Gradient Formula for Back Propagation Neural Network AlgorithmAbbas Y. Al Bayati, Najmaddin A. Sulaiman, Gulnar W. SadiqProblem statement: The Conjugate Gradient (CG) algorithm which usually used for solving nonlinear functions is presented and is combined with the modified Back Propagation (BP) algorithm yielding a new fast training multilayer algorithm. Approach: This study consisted of determination of new search directions by exploiting the information calculated by gradient descent as well as the previous search direction. The proposed … …Journal of Computer Science, Vol. 5, Issue 11 · 30 Dec 2009 · 6,989 accessesView PDFCite
Research ArticleOpen accessIn the abstractNew Constructive Neural Network Architecture for Pattern ClassificationS. S. Sridhar, M. PonnavaikkoProblem statement: Constructive neural network learning algorithms provide optimal ways to determine the architecture of a multi layer perceptron network along with learning algorithms for determining appropriate weights for pattern classification problems. These algorithms initially start with small network and dynamically allow the network to grow by adding and training neurons as needed until a satisfactory solution is found. The … …Journal of Computer Science, Vol. 5, Issue 11 · 30 Nov 2009 · 6,565 accessesView PDFCite
Research ArticleOpen accessIn the abstractBoosting Kernel Discriminative Common Vectors for Face RecognitionC. Lakshmi, M. PonnavaikkoProblem statement: Kernel discriminative common vector (KDCV) was one of the most effective non-linear techniques for feature extraction from high dimensional data including images and text data. Approach: This study presented a new algorithm called Boosting Kernel Discriminative Common Vector (BKDCV) to further improve the overall performance of KDCV by integrating the boosting and KDCV techniques. Results: In BKDCV, the … …Journal of Computer Science, Vol. 5, Issue 11 · 30 Nov 2009 · 6,571 accessesView PDFCite
Research ArticleOpen accessIn the abstractImproving Accuracy and Coverage of Data Mining Systems that are Built from Noisy Datasets: A New ModelLuai A. Al ShalabiProblem statement: Noise within datasets has to be dealt with under most circumstances. This noise includes misclassified data or information as well as missing data or information. Simple human error is considered as misclassification. These errors will decrease the accuracy of the data mining system so it will not be likely to be used. The objective was to propose an … …Journal of Computer Science, Vol. 5, Issue 2 · 28 Feb 2009 · 7,820 accessesView PDFCite
Research ArticleOpen accessIn the abstractRe-quantization Codebook Using FingerprintZ. F. Muhsen, M. A. Dababna, A. A. NsourRe-quantization is a key technology for reducing the bit rate of compressed data. The reduction of the bit rate and in certain cases may result in signal quality degradation. Techniques need to be deployed to enhance the signal quality based on optimization techniques. The proposed scheme constructed an optimal re-quantization codebook in an iterative manner for a given original quantization … …Journal of Computer Science, Vol. 4, Issue 11 · 30 Nov 2008 · 6,905 accessesView PDFCite