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.
In this paper, we implement hybrid Woodward-Lawson Neural Networks and weighted Fourier method to synthesize antenna arrays. The neural networks (NN) is applied here to simplify the modeling of MIMO antenna arrays by assessing phases. The main problem is obviously to find optimal weights of the linear antenna array elements giving radiation pattern with minimum sidelobe level (SLL) and hence ameliorating...
Bearings are widely used in industrial equipment, and their fault detections have tight relationship with the safety production and economic operation. Its running state can influence the performance of the whole machine directly, and the fault of bearing is one of the main factors that lead to the fault of machinery equipment during the running process. Instead of using traditional measures based...
Deep Neural Networks trained on large datasets can be easily transferred to new domains with far fewer labeled examples by a process called fine-tuning. This has the advantage that representations learned in the large source domain can be exploited on smaller target domains. However, networks designed to be optimal for the source task are often prohibitively large for the target task. In this work...
The deployment of deep convolutional neural networks (CNNs) in many real world applications is largely hindered by their high computational cost. In this paper, we propose a novel learning scheme for CNNs to simultaneously 1) reduce the model size; 2) decrease the run-time memory footprint; and 3) lower the number of computing operations, without compromising accuracy. This is achieved by enforcing...
Although Deep Convolutional Neural Networks (CNNs) have liberated their power in various computer vision tasks, the most important components of CNN, convolutional layers and fully connected layers, are still limited to linear transformations. In this paper, we propose a novel Factorized Bilinear (FB) layer to model the pairwise feature interactions by considering the quadratic terms in the transformations...
In this paper, we reveal the importance and benefits of introducing second-order operations into deep neural networks. We propose a novel approach named Second-Order Response Transform (SORT), which appends element-wise product transform to the linear sum of a two-branch network module. A direct advantage of SORT is to facilitate cross-branch response propagation, so that each branch can update its...
At present, the detection of mixing uniformity in glass furnace batching system is mainly realized by artificial detection. However, this method is time-consuming and laborious, and there are some risks. For the problem of mixing uniformity detection, the nonlinear relation between the actual weight value and the mixing uniformity is established by the BP neural network, which can predict the mixing...
In conventional echo stat network (ESN), the reservoir are randomly generated, then the spectral radius of the reservoir is scaled to lower than 1. In this method, only the necessary condition for echo state property (ESP) of ESN is satisfied while the sufficient condition is ignored, thus the ESN stability may not be ensured. In this paper, with the predefined singular values (smaller than 1), the...
Food safety is one of the hot issues in all over the world. It is related to national economy and people's livelihood. In recent years, food safety accidents occur in China frequently, so an effective food safety network public opinion early warning model is necessary and imperative. Therefore, the model of Back Propagation neural network based on Analytic Hierarchy Process (AHP-BP) is proposed. The...
Convolutional Neural Networks (CNNs) are well established models capable of achieving state-of-the-art classification accuracy for various computer vision tasks. However, they are becoming increasingly larger, using millions of parameters, while they are restricted to handling images of fixed size. In this paper, a quantization-based approach, inspired from the well-known Bag-of-Features model, is...
Dropout is a very effective way of regularizing neural networks. Stochastically “dropping out” units with a certain probability discourages over-specific co-adaptations of feature detectors, preventing overfitting and improving network generalization. Besides, Dropout can be interpreted as an approximate model aggregation technique, where an exponential number of smaller networks are averaged in order...
Training deep neural networks is difficult for the pathological curvature problem. Re-parameterization is an effective way to relieve the problem by learning the curvature approximately or constraining the solutions of weights with good properties for optimization. This paper proposes to reparameterize the input weight of each neuron in deep neural networks by normalizing it with zero-mean and unit-norm,...
Learned boundary maps are known to outperform handcrafted ones as a basis for the watershed algorithm. We show, for the first time, how to train watershed computation jointly with boundary map prediction. The estimator for the merging priorities is cast as a neural network that is convolutional (over space) and recurrent (over iterations). The latter allows learning of complex shape priors. The method...
In the field of connectomics, neuroscientists seek to identify cortical connectivity comprehensively. Neuronal boundary detection from the Electron Microscopy (EM) images is often done to assist the automatic reconstruction of neuronal circuit. But the segmentation of EM images is a challenging problem, as it requires the detector to be able to detect both filament-like thin and blob-like thick membrane,...
In this work we propose a novel framework named Dual-Net aiming at learning more accurate representation for image recognition. Here two parallel neural networks are coordinated to learn complementary features and thus a wider network is constructed. Specifically, we logically divide an end-to-end deep convolutional neural network into two functional parts, i.e., feature extractor and image classifier...
The purpose of this paper is to develop and analyses device capable of identifying sign language. The recognition is performed using Multilayer Perceptron and all the input data are signals from flex sensors, accelerometers and gyroscopes. Artificial Neural Network is tested modifying parameters as: a) number of neurons in only middle layer, b) learning rate between input and middle layers and c)...
This paper proposes a development's prediction model based on Artificial Neural Network. The methodology proposed consists in: i) countries selection; ii) selection and obtainment of indicators referring to the selected countries; iii) proposal prediction model; iv) Artificial Neural Network training and validation. The results indicated predicted values close to the real values of the Brazilian indicators...
Deep neural networks enjoy high interest and have become the state-of-art methods in many fields of machine learning recently. Still, there is no easy way for a choice of network architecture. However, the choice of architecture can significantly influence the network performance. This work is the first step towards an automatic architecture design. We propose a genetic algorithm for an optimization...
The paper presents aspects related to developing methods for financial time series forecasting using deep learning in relation to multi-agent stock trading system, called A-Trader. On the basis of this model, an investment strategies in A-Trader system can be build. The first part of the paper briefly discusses a problem of financial time series on FOREX market. Classical neural networks and deep...
In this paper, an approach to evaluating game states of a collectible card game Hearthstone is described. A deep neural network is employed to predict the probability of winning associated with a given game state. Encoding the game state as an input vector is based on another neural network, an autoencoder with a sparsity-inducing loss. The autoencoder encodes minion information in a sparse-like fashion...
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.