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.
Sparsity-inducing penalties are useful tools in variational methods for machine learning. In this paper, we propose two block-coordinate descent strategies for learning a sparse multiclass support vector machine. The first one works by selecting a subset of features to be updated at each iteration, while the second one performs the selection among the training samples. These algorithms can be efficiently...
Deep neural network (DNN) is trained according to a mini-batch optimization based on the stochastic gradient descent algorithm. Such a stochastic learning suffers from instability in parameter updating and may easily trap into local optimum. This study deals with the stability of stochastic learning by reducing the variance of gradients in optimization procedure. We upgrade the optimization from the...
Domain adaptation (DA) algorithms address the problem of distribution shift between training and testing data. Recent approaches transform data into a shared subspace by minimizing the shift between their marginal distributions. We propose a method to learn a common subspace that will leverage the class conditional distributions of training samples along with reducing the marginal distribution shift...
In this paper we propose a novel algorithm, which is an improvement for one-stage dictionary learning (OS-DL) algorithm, by imposing a l2-norm constraint on the update of the atoms. Our contribution embarks from the OS-DL algorithm and incorporates the well-known convex optimization method, proximal point method, into this algorithm. Experimental results on recovering a known dictionary and sparsely...
The weight initialization implementation is related to the convergence of any learning/training algorithm. In this paper we have analyzed Gradient Descent with Momentum Back propagation algorithm using eight different approximation functions and Nguyen & Widrow weight initialization method. We found that the best performance results are obtained using fifth approximation problem. The best performance...
Data clustering is one of the widely used data analysis methods which groups the unlabeled data into similar clusters. Classical data clustering methods under-performs to cluster multi-dimensional dataset such as micro arrays datasets. Therefore, this paper introduces a novel metaheuristic gauss-based cuckoo search clustering method to extend the capabilities of traditional clustering methods. The...
A method for hybridizing supervised learning with adaptive dynamic programming was developed to increase the speed, quality, and robustness of on-line neural network learning from an imperfect teacher. Reinforcement learning is used to modify and enhance the original supervisory signal before learning occurs. This paper describes the method of hybridization and presents a model problem in which a...
BP neural network is one of traditional methods to solve the inverse problems in Electrical Capacitance Tomography (ECT). To adopt this method, simple problems in industry can be solved well, but for the actual complicated industry environment it is limited. In this paper, based on the analysis of disadvantages in traditional BP neural network, adaptively adjustment learning rate is adopted and additional...
Traditional nonnegative matrix factorization (NMF) is an unsupervised method for linear feature extraction. Recently, NMF with block strategy is shown to be able to extract more sparse and discriminative information of the images. To enhance the discriminative power of NMF, this paper proposes a block kernel nonnegative matrix factorization (BKNMF) based on the kernel theory and block technique. Kernel...
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...
In this paper, convolutional neural networks (CNNs) is employed for remote-sensing scene classification, which fully utilizes the semantic features extracted from the images while ignoring some traditional features. Consider the limited labeled samples, CaffeNet model as the pre-trained architecture is adopted. By fine-tuning the pre-trained models, the proposed method is expected to be robust and...
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,...
This paper presents a new algorithm called Feature Selection Age Layered Population Structure (FSALPS) for feature subset selection and classification of varied supervised learning tasks. FSALPS is a modification of Hornby's ALPS algorithm — an evolutionary algorithm renown for avoiding pre-mature convergence on difficult problems. FSALPS uses a novel frequency count system to rank features in the...
A learning process is easily trapped into a local minimum when training multi-layer feed-forward neural networks. An algorithm called Wrong Output Modification (WOM) was proposed to help a learning process escape from local minima, but WOM still cannot totally solve the local minimum problem. Moreover, there is no performance analysis to show that the learning has a higher probability of converging...
The Support Vector Machines (SVMs) dual formulation has a non-separable structure that makes the design of a convergent distributed algorithm a very difficult task. Recently some separable and distributable reformulations of the SVM training problem have been obtained by fixing one primal variable. While this strategy seems effective for some applications, in certain cases it could be weak since it...
Delay learning in SpikeProp is useful because it eliminates the need of redundant synaptic connections in a Spiking Neural Network (SNN). The delay learning enhancement to SpikeProp, however, also inherits the complications present in basic SpikeProp with weight update that obstruct the learning process. To tackle these issues, we perform delay convergence analysis to investigate the conditions required...
Past research on Multitask Learning (MTL) has focused mainly on devising adequate regularizers and less on their scalability. In this paper, we present a method to scale up MTL methods which penalize the variance of the task weight vectors. The method builds upon the alternating direction method of multipliers to decouple the variance regularizer. It can be efficiently implemented by a distributed...
We consider learning problems over training sets in which both, the number of training examples and the dimension of the feature vectors, are large. To solve these problems we propose the random parallel stochastic algorithm (RAPSA). We call the algorithm random parallel because it utilizes multiple processors to operate in a randomly chosen subset of blocks of the feature vector. We call the algorithm...
We consider the problem of designing transmit and receive precoders to minimize the number of backlogged packets at the base stations (BSs) in a multiple-input multiple-output (MIMO)-orthogonal frequency division multiplexing (OFDM) scenario. Due to the nonconvex nature of the problem, we propose an iterative method for designing transmit precoders and receive beamformers. Since the overhead involved...
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.