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.
A model based Bayesian network (CRMBBN) is presented with classical conditional behaviors. A new concept about sense is introduced, the model regards sense as input and output sense prediction of next time. Reflex is not involved in CRMBBN, the non-classical conditional reflex is put into the instinctive behavior of the agent. So the model constructs Cause-Effect relationships between classical conditional...
On the base of Hopfield neural network, the minimum of feeder looses is treated as the target function. Because the distribution network is radical, we put forward a method for deciding each node's in-degree by using Hopfield neural network. According to each node's in-degree, it can be easily determined whether the line will be used or not. So the state of switch and the scheme of reconfiguration...
There are two problems when conditional T-S fuzzy neural network is used directly in speech recognition system. One is the rule disaster problem, that is, the rule number will increase exponentially with the increase of input dimensions. Another problem is the network reasoning failure resulted from input dimensions too large. The paper presented an improved algorithm of T-S fuzzy neural network....
This paper uses a hybrid genetic learning algorithm to train Pi-sigma neural network and this algorithm was once applied to resolve a function optimizing problem. The hybrid genetic learning algorithm incorporates the stronger global search of genetic algorithm into the stronger local search of flexible polyhedron method, and can search out the global optimum faster than standard genetic algorithm...
Acquisition of abstract concept is the key step in human intelligence development, but the neural mechanism of concept formation is not clear yet. Researches on complexity and self organization theory indicate that concept is a result of emergence of neural system and it should be represented by an attractor. Associative learning and hypothesis elimination are considered as the mechanisms of concept...
Nowadays, face detection and recognition have gained importance in security and information access. In this paper, an efficient method of face detection based on principal components analysis (PCA) and support vector machine (SVM) is proposed. It firsly filter the face potential area using statistical feature which is generated by analyzing local histogram distribution. And then, SVM classifier is...
In this paper, we propose a novel nonlinear ensemble rainfall forecasting model integrating generalized linear regression with artificial neural networks (ANNs). In this model, using different linear regression extract linear characteristics of rainfall system. Then using different ANNs algorithms and different network architecture extract nonlinear characteristics of rainfall system. Thirdly, the...
Among the research of artificial neural networks, the most important problem is how to select the appropriate parameters for an artificial neural network. In this paper, a new evolutionary algorithm called region reproduction algorithm (RRA) is introduced to optimize the parameters of neural networks. The algorithm firstly generates some regions in space and then the offspring in the region is reproduced...
In order to mine important information in hydrologic series data adequately and improve results of mid-to-long term runoff forecast, factors influencing forecast results have been analyzed firstly, and a stochastic model for mid-to-long term runoff forecast has been established based on WA, ANN, and hydrologic frequency analysis. The main idea is: analyze runoff series in multi time scales by WA firstly,...
In this work, we propose a kind of supervised classification - support vector machine (SVM) to segment magnetic resonance image (MRI). As a classifier, SVM can employ structural risk minimization principle and perform better in classification task. Based on those excellent capabilities of SVM, we conduct many detailed experiments on some standard simulated data and real data. According to the experiments...
To ensure fast adaptation and security of social and computerized systems to changing environments, targets of perceptron based classifiers ought to vary during training process. To determine optimal differences between target values (stimulation, arousal) we suggest using genetically evolving multi-agent systems aimed to extract necessary information from sequences of the changes. A specially designed...
According to dynamic information processing problems concerning process fuzzy information or domain rules, this paper presents a weighted fuzzy reasoning process neuron and a weighted fuzzy reasoning process neural network model. The weighted fuzzy reasoning process neuron uses dynamic information processing methods of fuzzy process reasoning rules and numerical process neuron in combination, and...
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.