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.
Imperialist Competitive Algorithm (ICA) is a novel optimization algorithm that inspired by socio-political process of imperialistic competition. ICA shown its excellent capability in diverse optimization tasks. In this paper, a new method for training an Artificial Neural Network using Chaotic Imperialist Competitive Algorithm is proposed. In Chaotic Imperialist Competitive Algorithm (CICA) the chaos...
Combining particle swarm optimization algorithm (PSO) with cultural algorithm (CA), a new cultural particle swarm optimization algorithm (CPSO) is proposed by this paper. Then, Both CPSO and PSO are used to resolve the optimization problems of five widely used test functions, and the results show that CPSO has better optimization performance than PSO. Next, CPSO is applied to train artificial neural...
A new optimal design strategy for monohull vessels is proposed. The goal of the proposed procedure is to make monohulls competitive with their multihull counterparts. The resulting designs, thus, would combine the advantages of high speed vessels with those of simpler monohull vessels. The proposed strategy proposes a new re-formulation of hull optimization problem objective and uses a new class of...
As one of the extensive applications of artificial neural network, BP algorithm has some shortcomings such as local optimum. In this paper, we propose a new method--TACO-BP algorithm to train neural network, which may overcome the shortcoming. Firstly, we give description about the TACO-BP. After experiments, we compare the performance between TACO-BPNN and BPNN. Lastly, we analyze the results of...
A new ANN (artificial neural network) structure is proposed to learn dynamics model of robot. The characterizing feature is that some integral units are appended to a recurrent ANN structure, so it can image dynamic process commendably. Generalization capacity of the learning dynamics model is discussed, as well as its application in optimization, etc. The effectiveness of the method is confirmed...
An improved particle swarm optimizer based on differential evolution theory is proposed. This algorithm introduces differential mutation operator into the basic particle swarm optimizer in order to solve the premature convergence problem. And this new algorithm was used to training weights and thresholds of feedforward neural network, simulation results show that this approach is effective and has...
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.