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 deals with the problem of assigning tasks to a set of nodes communicating in a connected graph topology to satisfy the following requirements: assigning all the tasks to the agents; assigning to each agent no more than M tasks; minimizing the maximum total load of each agent. A gossip-based algorithm is presented: starting from an unfeasible solution, at each iteration a node solves a Local-Integer...
Particle swarm optimisation has been successfully applied as a neural network training algorithm before, often outperforming traditional gradient-based approaches. However, recent studies have shown that particle swarm optimisation does not scale very well, and performs poorly on high-dimensional neural network architectures. This paper hypothesises that hidden layer saturation is a significant factor...
Agents of a network have access to strongly convex local functions fi and attempt to minimize the aggregate function f(x) = Σi=1nfi(x) while relying on variable exchanges with neighboring nodes. Various methods to solve this distributed optimization problem exist but they all rely on first order information. This paper introduces Network Newton, a method that incorporates second order information...
Deep neural networks (DNN) are typically optimized with stochastic gradient descent (SGD) using a fixed learning rate or an adaptive learning rate approach (ADAGRAD). In this paper, we introduce a new learning rule for neural networks that is based on an auxiliary function technique without parameter tuning. Instead of minimizing the objective function, a quadratic auxiliary function is recursively...
For structural optimization of neural networks, i.e., the challenging problem to determine the number of hidden layers and the number of neurons, we propose a structural optimization algorithm based on an improved genetic algorithm (IGA). The proposed algorithm is then employed to approximate nonlinear function y=e−(x−1)2+e−(x+1)2 in MATLAB. Extensive simulation demonstrates that the proposed optimization...
Outlier detection is fundamental to a variety of database and analytic tasks. Recently, distance-based outlier detection has emerged as a viable and scalable alternative to traditional statistical and geometric approaches. In this article we explore the role of ranking for the efficient discovery of distance-based outliers from large high dimensional data sets. Specifically, we develop a light-weight...
In order to deal with the defects of the poor convergences and easily immerging in partial minimum frequently, a new algorithm is proposed based on the combination of genetic algorithm and BP neural network, which is called GA- BP algorithm. This algorithm is applied to optimization of initial weights of BP Network, the structure and learn rule. It searches through the total solution space and can...
The Extreme Learning Machine (ELM) is a recent algorithm for training single-hidden layer feedforward neural networks (SLFN) which has shown promising results when compared with other usual tools. ELM randomly chooses weights and biases of hidden nodes and analytically obtains the output weights and biases. It constitutes a very fast algorithm with a good generalization performance in most cases....
The future marine traffic accident situation is shown by using the marine traffic accident prediction method. Thus, marine traffic accident prediction method based on particle swarm optimization-based RBF neural network is presented in the paper. Particle swarm optimization algorithm, a kind of population-based optimization algorithm, is used to adjust the connection weights and the center and width...
The convex approach to the absolute stability problem is considered. Gapski and Geromel's algorithm for computing Zames-Falb multipliers, used in determining stability, treats the problem as an optimization problem. It is found that their algorithm may terminate prematurely in some cases, failing to find the optimal multiplier. We propose an improvement that always finds an ascent direction and a...
To address the unconstrained optimization problem, the Conjugate Gradient Method (CG) uses the sequence of iterations to approach the minimum point of aim function. Because of the effect of rounding errors, many merits of CG are no longer in existence in practical use. Hence the rate of convergence is not ideal and a practical problem confronting us is how to improve conjugate gradient iteration so...
A common drawback of standard reinforcement learning algorithms is their inability to scale-up to real-world problems. For this reason, a current important trend of research is (state-action) value function approximation. A prominent value function approximator is the least-squares temporal differences (LSTD) algorithm. However, for technical reasons, linearity is mandatory: the parameterization of...
This paper presents how credibility theory and chance-constrained optimization method can be efficiently applied for modelling and solving agricultural production planning problem in fuzzy systems. Since the proposed fuzzy agricultural production planning chance-constrained model includes fuzzy variable coefficients defined through possibility distributions with infinite supports, it is infinite-dimensional...
The last few years have seen a significant growth in communication networks. With the growth of data traffic, network operators seek network-engineering tools to extract the maximum benefits out of the existing infrastructure. This has suggested a number of new optimisation problems, most of them in the field of combinatorial optimisation. We address here the Terminal Assignment problem. The main...
A parallel chaos optimization algorithm based on probability selection is proposed to resolve the function optimization problems. The searching space divides into origin space and elaborate space. During the optimization, the two spaces are searched synchronously according to different probability. The boundary of the elaborate space is decreased continuously, and its searching probability is increased...
TSP (Traveling Salesman Problem) is a kind of typical NP problems, mostly settled by genetic algorithm (GA). Differential Evolution Algorithm (DE) is a kind of new Evolution Algorithm which has many similarities with GA. We proposed to solve TSP problem by improved differential evolution algorithm. Added an auxiliary operator for regulating integer sequence to mutation process, and replaced the original...
The radial basis function (RBF) is well known dynamic recursion neural network. However, RBF weights and thresholds, which are trained by back propagation algorithm, the gradient descent method and genetic algorithm, will be fixed after the training completing. The adaptive ability is bad. To improve RBF identification performance, particle swarm optimization (PSO), which is a stochastic search algorithm,...
For the shortcoming of Particle Swarm Optimization (PSO) algorithm in Wavelet Neural Network (WNN) training, a modeling approach of WNN based on improved PSO algorithm is proposed. The approach applied a PSO algorithm based on the strategies of multi-particle information sharing and self-adaptive inertia weight to optimize the parameters of WNN for modeling quality of WNN. The experiment result indicates...
To reduce the computational burden of the nearest neighbor search (NNS) problem, most existing algorithms focus on `preprocessing' the data set to reduce the number of objects to be examined for each querying operation (e.g., efficient data structures, metric space transforms). In this paper we present a quantization based nearest-neighbor-preserving metric approximation algorithm (QNNM) that leads...
Response to the question that the traditional gain scheduling which is one-parameter adjusting is complex and difficult to find suitable adjusting rule and so the flying qualities in full flight envelope curve specially for those flight conditions between the operating points can’t be guaranteed for a modern fly-by-wire flight control system, a design method of three-layer BP network gaining-scheduling...
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.