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.
Joint sparse representation (JSR) models have been widely applied into the field of hyperspectral image (HSI) classification. However, most of JSR-based models adopt the Frobenius norm to measure the reconstruction error, which ignores the structural information of the small patch. In this paper, we propose a nuclear-norm joint sparse representation (NuJSR) model for hyperspectral image classification...
Deep embeddings answer one simple question: How similar are two images? Learning these embeddings is the bedrock of verification, zero-shot learning, and visual search. The most prominent approaches optimize a deep convolutional network with a suitable loss function, such as contrastive loss or triplet loss. While a rich line of work focuses solely on the loss functions, we show in this paper that...
Nowadays, applications based on digits recognition and characters recognition have become much more reliable thanks to the rapid development of the DNN(deep neural network) architecture and constantly increasing the efficiency to the computing resources. A lot of methods have been proposed to improve the performance of DNNs, such as the ReLU (Rectified Linear Unit) which is a widely used alternative...
Vehicle logo recognition is an important part of vehicle identification in intelligent transportation systems. State-of-the-art vehicle logo recognition approaches typically consider training models on large datasets. However, there might only be a small training dataset to start with and more images can be obtained during the real-time applications. This paper proposes an online image recognition...
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...
In this work we propose an accelerated stochastic learning system for very large-scale applications. Acceleration is achieved by mapping the training algorithm onto massively parallel processors: we demonstrate a parallel, asynchronous GPU implementation of the widely used stochastic coordinate descent/ascent algorithm that can provide up to 35× speed-up over a sequential CPU implementation. In order...
Classification is at the very center of the supervised learning. In this work, we propose a novel algorithm to classify the test data set with the aid of a vector field, emanating from the training data set. In particular, the vector field is constructed such that the location of each training data point becomes a local minimum of the potential. The test data points are allowed to evolve under the...
In this paper, we focus on training a classifier from large-scale data with incompletely assigned labels. In other words, we treat samples with following properties: 1. assigned labels are definitely positive, 2. absent labels are not necessarily negative, and 3. samples are allowed to take more than one label. These properties are frequently found in various kinds of computer vision tasks, including...
Anomaly detection (AD) involves detecting abnormality from normality and has a wide spectrum of applications in reality. Kernel-based methods for AD have been proven robust with diverse data distributions and offering good generalization ability. Stochastic gradient descent (SGD) method has recently emerged as a promising framework to devise ultra-fast learning methods. In this paper, we conjoin the...
To address the high-dimensionality of big data, numerous iterative algorithms have been introduced including least absolute shrinkage selection operator (Lasso) and iteratively sure independent screening (ISIS). However, the iterative nature of these algorithms renders the computational cost of retraining the learning model impractical. We take advantage of this key observation to propose a novel...
A method based on the information theory concept of entropy is presented for selecting subsets of data for offline model identification. By using entropy-based data selection instead of random equiprobable sampling before training models, significant improvements are achieved in parameter convergence, accuracy and generalisation ability. Furthermore, model evaluation metrics exhibit less variance,...
A novel active appearance model (AAM) search algorithm based on partial least squares (PLS) regression is proposed. PLS models the relationship between independent (texture residuals) and dependent (error in the model parameters) variables in the training phase by extracting from independent and dependent variables a set of orthogonal factors called latent variables respectively which have the maximum...
Engineering design process requires modeling and optimization to find optimum design parameters. While direct optimization only exploits time consuming but accurate fine model, surrogate based optimization exploits less accurate but fast coarse model to reduce the overall computational effort. In this work, space mapping with inverse difference technique is applied to antenna design problem together...
This paper discusses implementations of gradientdescent based learning algorithms on memristive crossbar arrays. The Unregulated Step Descent (USD) is described as a practical algorithm for feed-forward on-line training of large crossbar arrays. It allows fast feed-forward fully parallel on-line hardware based learning, without requiring accurate models of the memristor behaviour and precise control...
Network intrusion detection is the process of identifying malicious behaviors that target a network and its resources. Current systems implementing intrusion detection processes observe traffic at several data collecting points in the network but analysis is often centralized or partly centralized. These systems are not scalable and suffer from the single point of failure, i.e. attackers only need...
Recently, the application of complex-valued neural networks (CVNNs) for real-valued classification has attracted more and more attention. To overcome the limitations of the existing CVNNs, this study extends the real-valued group method of data handling (RGMDH) type neural network to complex domain, and constructs complex-valued GMDH-type neural network (CGMDH). First, it proposes the complex least...
We present an algorithm and implementation for distributed parallel training of single-machine multiclass SVMs. While there is ongoing and healthy debate about the best strategy for multiclass classification, there are some features of the single-machine approach that are not available when training alternatives such as one-vs-all, and that are quite complex for tree based methods. One obstacle to...
In this article, we propose a change detection technique using semi-supervised Hopfield-Type Neural Network (HTNN). The purpose of the work is to show the usefulness of semi-supervision over existing unsupervised/fully supervised methods when we have only a few labeled samples. Here, training of HTNN is performed iteratively using a few labeled patterns along with a number of unlabeled patterns. A...
The Back Propagation Neural Network(BPNN) has been used widely in objects recognition, but in fact, the BPNN can easily be trapped into a local minimum and has slow convergence. Moreover, the number of neural cells for hidden layer in the BPNN is hard to determine. For this reason, this paper proposes a novel method to improve the performance from the structure and the algorithm. The improved BP algorithm...
In this paper, we present a model based on the Neural Network (NN) for classifying Arabic texts. We propose the use of Singular Value Decomposition (SVD) as a preprocessor of NN with the aim of further reducing data in terms of both size and dimensionality. Indeed, the use of SVD makes data more amenable to classification and the convergence training process faster. Specifically, the effectiveness...
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.