The Infona portal uses cookies, i.e. strings of text saved by a browser on the user's device. The portal can access those files and use them to remember the user's data, such as their chosen settings (screen view, interface language, etc.), or their login data. By using the Infona portal the user accepts automatic saving and using this information for portal operation purposes. More information on the subject can be found in the Privacy Policy and Terms of Service. By closing this window the user confirms that they have read the information on cookie usage, and they accept the privacy policy and the way cookies are used by the portal. You can change the cookie settings in your browser.
This paper presents the analysis of results on the generalisation of dyadic based wavelet neural network which are trained with uniform distribution from input space. The focus is to mainly quantify the significance of learning rate and the resolution so as to ensure an acceptable generalization accuracy for function learning simulations. The proposed network is based on orthonormal basis functions...
In this paper we discuss various machine learning approaches used in mining of data. Further we distinguish between symbolic and sub-symbolic data mining methods. We also attempt to propose a hybrid method with the combination of Artificial Neural Network (ANN) and Cased Based Reasoning (CBR) in mining of data.
Medicine has always benefited from the technology. Artificial Neural Networks is currently the promising area of interest to solve medical problems. Diagnosis of diabetes is one of the most challenging problems in machine learning. This medical data set is seldom complete. Artificial neural networks require complete set of data for an accurate classification. The system explains how the pre-processing...
Gaussian process (GP) regression, a structured supervised learning alternative to neural networks for the fast modeling of antenna characteristics, is applied to modeling S11 and gain against frequency of a dual-band microstrip patch antenna with separate tuning strips on a three-layer substrate. Since the two frequency bands of the antenna are relatively narrow, the function underlying the variation...
In today's context, it is common to leave the house unattended as people are busy catching up with their tight daily schedule. Therefore, most people have chosen the home security system as the most reliable way to protect their home. However, the existing security mechanism provided by smart home is lack of intelligence for higher level decision making and action taking. Furthermore, the current...
This paper describes the possibilities of using artificial neural networks in the following fields of machine learning: data mining and semantic integration in large databases. Possibility of using analog components for developing neural networks is investigated.
Personal Credit Scoring is of great significance for commercial banks to circumvent credit consumption, the original BP algorithm's convergence rate is slow, learning precision is low, the training process is easy to fall into local minimum, this paper presents an improved algorithm with variable learning rate based on BP algorithm, and applied to simulate personal credit scoring. After comparing...
In this paper, we propose A two-stage learning scheme for neural networks by integrating Gas into Structure identification In the first stage, which is also called structure identification stage, the selection of network structure and initial parameters is carried out by float genetic algorithm instead of human ln the second stage which is called parameter identification stage the conventional optimization...
Defect detection on industrial flat surface products like textiles, steel slabs, metal plates, plastic films, painted car body, parquet slabs and paper is a necessary requirement for quality control and satisfaction of consumers. This paper presents a system for feature extraction and fusion in order to enhance the performance of the defect detection process. A multi-feature fusion technique based...
Powder Metallurgy (P/M) involves multiple input and output which are non-linearly related for which statistical optimization methods are not suitable. These considerations lead to adoption of neural network (NN) for proper selection of P/M process parameter. In the present work, white cast iron powder is taken as the work material and NN approach is employed which allows specification of multiple...
A capacitorless all-OTA bandpass biquad is tuned by utilizing an artificial neural network (ANN) with updated training sets. The training set contains a few tens samples which is varying in experiment. The training set is selected from predefine bias points that are closing to the desired biquad requirement. A second-order bandpass requirement, centered at 406.2 MHz, is successfully tuned as a sample...
This paper describes a method for improving the generalization performance of bagging ensemble by means of using Bayesian approach. We examine the Bayesian prediction using bagging leaning machines for regression problems, and show a method to reduce the generalization loss defined by the square error of the prediction for test data. We examine and validate the effectiveness via numerical experiments...
In this paper, we investigate the ability of a radial basis function network to determine the values of the watermark to be inserted in a 3D triangulated mesh model. The challenge in a watermarking algorithm is to achieve high watermark embedding capacity without causing perceptual distortion to the model. The proposed technique overcomes this challenge. The principal, mean and Gaussian curvature...
Ensembles with several neural networks are widely used to improve the generalization performance over a single network. Proper diversity among component networks is considered an important parameter for ensemble construction so that failure of one may be compensated by others. Data sampling, i.e., different training sets for different networks, is the most investigated technique for diversity than...
How to transfer GPS heights into normal heights has become a hotspot in survey engineering. With the development of computer and information technology, artificial neural networks (ANN) has been used widely, which has the character of the high parallel distributed processing, associative memory abilities, self-organization, self-learning and strong nonlinear mapping abilities, and the theory has proved...
This paper gives a deep investigation into AdaBoost algorithm, which is used to boost the performance of any given learning algorithm. Within AdaBoost, weak learners are crucial and primitive parts of the algorithm. Since weak learners are required to train with weights, two types of weak learners: artificial neural network weak learner and naive Bayes weak learner are designed. The results show AdaBoost...
Learning to rank is an important area at the interface of machine learning, information retrieval and Web search. The central challenge in optimizing various measures of ranking loss is that the objectives tend to be non-convex and discontinuous. To make such functions amenable to gradient based optimization procedures one needs to design clever bounds. In recent years, boosting, neural networks,...
Artificial Neural Networks (ANN) is gaining significant importance for pattern recognition applications particularly in the medical field. A hybrid neural network such as Counter Propagation Neural Network (CPN) is highly desirable since it comprises the advantages of supervised and unsupervised training methodologies. Even though it guarantees high accuracy, the network is computationally non-feasible...
Propose a wavelet neural network (WNN) sound source model based on Shuffled Frog Leaping Algorithm (SFLA). Utilize frog leaping algorithm to optimize weights and thresholds of WNN, obtain initial weights and thresholds possessing certain ergodicity and then train WNN. It overcomes disadvantages of neural network that has slower searching speed and easily falls into local extremum. Simulation results...
In Grid computing resource selection is a challenging problem, because Grid scheduler is usually operating in a dynamic and uncertain environment. Conventional scheduling algorithms will fail due to the static rules specified at design time and much user intervention required. Neural networks with a fast and accurate learning paradigm are promising to solve the Grid resource selection problem. This...
Set the date range to filter the displayed results. You can set a starting date, ending date or both. You can enter the dates manually or choose them from the calendar.