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.
Deep multi-layer neural networks are generally trained using variants of the gradient descent based algorithm. However, this kind of algorithms usually encounter a series of shortcomings, such as low training efficiency, local minimum, difficult control parameter tuning, and gradient vanishing or exploding. Besides, for a specific application, how to design the structure of the network, that is, how...
Image annotation is a hard multi-label learning problem which aims at automatically tagging each input image with relevant keywords reflecting its semantic concepts. Recently, several late fusion methods were proposed to improve the accuracy of image annotation. But these late fusion methods need normalization of confidence score vectors of independent models corresponding to distinct representations...
Sparse matrix-vector multiplication (SpMV) is a key operation in scientific computing and engineering ap-plications. This paper presents an optimization strategy to improve SpMV performance on the multi-GPU systems by adopting OpenMP threads and multiple CUDA streams. We propose an efficient scheme to control multiple GPUs jointly complete SpMV computations by making use of OpenMP threads. Moreover,...
The success of deep learning proves that deep models are able to achieve much better performance than shallow models in representation learning. However, deep neural networks with auto-encoder stacked structure suffer from low learning efficiency since common used training algorithms are variations of iterative algorithms based on the time-consuming gradient descent, especially when the network structure...
Vehicular network is regarded as an important part of the Intelligent Transportation System (ITS). However, with the increasing number of vehicular applications, it is a challenge to meet the demands of both communication and computation. Fog computing can provide mobile users with the demanded services through low latency and short-distance local connections. This paper investigates the optimal deployment...
To satisfy the stringent requirement of ocean monitoring in Marine Intelligent Transportation System, Marine Sensor Networks (MSNs) is envisioned as one of the most effective solutions. In this paper, we study the Heterogeneous and Double Paths MSNs (HDPM) architecture with Sensors (SNs) in view of the reliability of the networks. And we propose a generic integer linear programming (ILP) model to...
In this paper, the Harmony Search (HS)-based BP neural networks are used for the classification of the epileptic electroencephalogram (EEG) signals. It is well known that the gradient descent-based learning method can result in local optima in the training of BP neural networks, which may significantly affect their approximation performances. Two HS methods, the original version and a new variation...
Ant Colony Optimization algorithms often suffer from criticism for the local optimization and premature convergence. In this paper, we introduce several main ant algorithms, analyze their design ideas, and draw the conclusion that biases in transition rules and update rules are the root cause of the local optimization and premature convergence. Inspired by the adaptive behaviors of some Monomorium...
The purpose of fusion the multispectral (MS) and panchromatic (PAN) remote sensing images is to obtain high spatial resolution and quality of the PAN image as well as to preserve spectral information of the MS image. The parameter selection of fusion rule will directly affect the fusion result. In this paper, a new fusion method is presented based on multi-objective evolutionary algorithm (called...
In this paper, we first describe the basic principle and the method of the A* algorithm. And we analyze the reason that the A* algorithm influences speed when it is searching for the optimum route in network game map. Then we give the optimization scheme from the aspects of node data structure to the maintenance of the open queue. At the same time, the optimization scheme is evaluated and tested by...
With the enlargement of sizes of networks, scale-free property of networks is present. However, scale-free networks are fragile. If the nodes with most degree are attacked, the whole network will be devastated. This paper proposed an algorithm to optimize the topology of scale-free networks with redundant edges. Adjacent networks of key nodes will be linked as a rotary and junction structure, to ensure...
Computer-based tests have been proven to be more effective and efficient than traditional paper-and-pencil tests, so more and more examinations begin to offer computerized form, taking the Professional Qualification Examination for example. In this paper, according to the item bank and composition rules in the Professional Qualification Examination, we propose an intelligent test sheet composition...
This paper presents a novel competitive neural network learning approach to schedule requests to a cluster of Web servers. In our new method one of the two main purposes was to try the advantage and effectiveness of the artificial neural networks to produce a triangular grid, where first an artificial neural network is used to order the data and form a grid of control vertices with triangle topology,...
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.