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 develops a distributed stochastic subgrandient-based support vector machine algorithm when training data to train support vector machines are distributed in the network. In this situation, all the data are decentralized stored and unavailable to all agents and each agent has to make its own update based on its computation and communication with neighbors. With mild connectivity conditions,...
This paper investigates an event-triggered distributed cooperative learning (DCL) algorithm using radial basis function networks (RBFNs), where training samples are often extremely large-scale, high-dimensional and located on distributed nodes over strongly connected and weight-balanced networks. The algorithm is based on Zero-Gradient-Sum (ZGS) distributed optimization strategy and works in a fully...
Discriminative dictionary learning has been widely used in many applications such as face retrieval / recognition and image classification, where the labels of the training data are utilized to improve the discriminative power of the learned dictionary. This paper deals with a new problem of learning a dictionary for associating pairs of images in applications such as face image retrieval. Compared...
Stationarity of reconstruction problems is the crux to enabling convolutional neural networks for many image processing tasks: the output estimate for a pixel is generally not dependent on its location within the image but only on its immediate neighbourhood. We expect other invariances, too. For most pixel-processing tasks, rigid transformations should commute with the processing: a rigid transformation...
Rectified linear units (ReLU) are known to be effective in many deep learning methods. Inspired by linear-mapping technique used in other super-resolution (SR) methods, we reinterpret ReLU into point-wise multiplication of an identity mapping and a switch, and finally present a novel nonlinear unit, called a selection unit (SU). While conventional ReLU has no direct control through which data is passed,...
Construction of robust and accurate deep neural networks (DNNs) is a computationally demanding and time-consuming process. Such networks also end up being memory intensive. Today, there is ever-increasing need to provide proactive and personalized support for users of smart devices. We could provide better personalization if we have the ability to update/train the DNN on edge devices. Also, by moving...
Opponent modeling is an essential approach for building competitive computer agents in imperfect information games. This paper presents a novel approach to accelerate the convergence process in opponent modeling. The approach applies neural network (ANN) to abstract and build an endgame data set of imperfect information game. Based on a labeled database of author's previous work, several parameters...
Super-resolution image reconstruction is one of the important issues in the field of computer vision. Machine learning is also the powerful method to solve the problem of computer vision. The method of SRCNN, which is put forward by Tang, is used for image super-resolution and shows the state-of-the-art performance. However, the method of SRCNN still has some shortcomings. On one hand, the training...
Feature selection is an important task in machine learning, which aims to reduce the dataset dimensionality while at least maintaining the classification performance. Particle Swarm Optimisation (PSO) has been widely applied to feature selection because of its effectiveness and efficiency. However, since feature selection is a challenging task with a complex search space, PSO easily gets stuck at...
In order to solve the multipath effect and non-ideal channel characteristics for unmanned aerial vehicle data link, this paper introduces the design of adaptive cascaded equalizer and its FPGA implementation. By cascading constant modulus algorithm (CMA) equalizer, digital phase locked loop (PLL) and decision feedback equalizer (DFE), adaptive cascaded equalizer achieves convergence through two manageable...
In this paper we propose a method for continuously processing and learning from data in Restricted Boltzmann Machines (RBMs). Traditionally, RBMs are trained using Contrastive Divergence (CD), which is an algorithm consisting of two phases, of which only one is driven by data. This not only prohibits training of RBMs in conjugation with continuous-time data streams, especially in event-based real-time...
ADP is an effective optimal method. However, the optimality depends on its network structure and training algorithm. This paper adopts RBF neural network to realize its critic and action networks after a detailed analysis on ADP. The LSM method is introduced as training algorithm, and a novel basis function is defined, which achieves global optimization and online control. The validity is verified...
Detecting Sybils in online social networks (OSNs) is a fundamental security research problem as adversaries can leverage Sybils to perform various malicious activities. Structure-based methods have been shown to be promising at detecting Sybils. Existing structure-based methods can be classified into two categories: Random Walk (RW)-based methods and Loop Belief Propagation (LBP)-based methods. RW-based...
P300-based brain-computer interface (BCI) is one of the most common BCIs. Due to the characteristics of P300 responses vary from person to person, it leads to the necessity of collecting much labeled data from each user and the problem of time-consuming in many applications. In this work, a transfer learning method which dynamically adjusts the weights of instances is applied to improve the P300-based...
Stochastic gradient descent (SGD) is a commonly used technique in large-scale machine learning tasks, but its convergence is slow due to the inherent variance. In recent years, a popular method, Stochastic Variance Reduced Gradient (SVRG), addresses this shortcoming via computing the full gradient of the entire dataset in each epoch. However, conventional SVRG and its variants usually need to identify...
Stochastic gradient algorithms are the main focus of large-scale optimization problems and led to important successes in the recent advancement of the deep learning algorithms. The convergence of SGD depends on the careful choice of learning rate and the amount of the noise in stochastic estimates of the gradients. In this paper, we propose an adaptive learning rate algorithm, which utilizes stochastic...
Carefully injected noise can speed the convergence and accuracy of video classification with recurrent backpropagation (RBP). This noise-boost uses the recent results that backpropagation is a special case of the generalized expectation maximization (EM) algorithm and that careful noise injection can always speed the average convergence of the EM algorithm to a local maximum of the log-likelihood...
This paper extends the random vector functional-link (RVFL) networks with single-hidden-layer to interval ones (IRVFLNs) with interval model parameters. The analytic solutions are derived for the interval network parameters using the well-known least square methods, which can overcome the problems such as local minimal, slow convergence. In order to evaluate the performance of IRVFLNs, we choose two...
A control theoretic approach is presented in this paper for both batch and instantaneous updates of weights in feed-forward neural networks. The popular Hamilton-Jacobi-Bellman (HJB) equation has been used to generate an optimal weight update law. The main contribution in this paper is that a closed form solutions for both optimal cost and weight update can be achieved for any feed-forward network...
Neural Networks have been successfully used in different fields of Information Security such that network intrusion detection and malware analysis because of ability to provide high level of abstraction for complex and incomplete data. Despite its successful application as off-line learning method, the on-line learning can be challenging when dealing with data streams. This paper presents an ongoing...
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.