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.
Data representation plays an important role in performance of machine learning algorithms. Since data usually lacks the desired quality, many efforts have been made to provide a more desirable representation of data. Among many different approaches, sparse data representation has gained popularity in recent years. In this paper, we propose a new sparse autoencoder by imposing the power two of smoothed...
State of the art methods in astronomical image reconstruction rely on the resolution of a regularized or constrained optimization problem. Solving this problem can be computationally intensive and usually leads to a quadratic or at least superlinear complexity w.r.t. the number of pixels in the image. We investigate in this work the use of convolutional neural networks for image reconstruction in...
In this paper, we develop a novel second-order method for training feed-forward neural nets. At each iteration, we construct a quadratic approximation to the cost function in a low-dimensional subspace. We minimize this approximation inside a trust region through a two-stage procedure: first inside the embedded positive curvature subspace, followed by a gradient descent step. This approach leads to...
In a game it is often the case that there are multiple roles or types of actors with different goals. One possible target for automatic content generation is to create multiple different software agents for these distinct roles. This paper outlines a technique, based on the multiple worlds model, for creating such actors via evolution. The objective function is based on the performance of the actors...
The increasing amount of data to be processed coming from multiple sources, as in the case of sensor networks, and the need to cope with constraints of security and privacy, make necessary the use of computationally efficient techniques on simple and cheap hardware architectures often distributed in pervasive scenarios. Random Vector Functional-Link is a neural network model usually adopted for processing...
This paper proposes a regrouping particle swarm optimization-based neural network (RegPSONN) for rolling bearing fault diagnosis. The proposed method applied neural network for rolling bearing conditions classification, and regrouping particle swarm optimization (RegPSO) is utilized for network training, and ten time-domain feature parameters are selected to establish the input vector. To evaluate...
Optimal slip rate identifier based on BP neural network has some bugs such that it is easy to fall into local minimum. In order to improve the aircraft's braking efficiency, this paper presents a new method for optimal slip rate identification based on firefly algorithm optimization. The proposed algorithm is used to optimize the weight value of BP neural network and the result shows that the algorithm...
In ultra-dense heterogeneous networks, caching popular contents at small base stations is considered as an effective way to reduce latency and redundant data transmission. Optimization of caching placement/replacement and content delivering can be computationally heavy, especially for large-scale networks. The provision of both time-efficient and high-quality solutions is challenging. Conventional...
In the multi-objective decision-making problems, the weight problem research occupies a very important position. The weight is the quantitative distribution of the different aspects' importance of the object to be evaluated, and the weight of each evaluation factor in the overall evaluation is differentiated, and is of great significance in practice. In this paper, by using the fuzzy analytic hierarchy...
Twin support vector regression and its extensions have been widely applied in machine learning and data mining. However, most of them can not achieve the satisfactory performances when the noise is involved. To this end, this paper presents a weighted least squares twin support vector regression (WLSTSVR) which can reduce the influence of the noise on prediction accuracy by using the information of...
Least squares support vector machines (LSSVM) has a good performance in small data samples, but can't solve the large-scale sample problems. In this paper, large data set sparse least squares support vector machines model based on stochastic entropy is proposed, and it can be applied to large-scale data samples. Firstly, the large-scale data set is divided into several subsets. Then the entropy method...
In this paper, evolutionary programming algorithm through the mutation operator and the selection strategy to find the optimal individual, used to initialize the BP neural network's weights and threshold value. Through this way, we can improve the training efficiency, speed up the convergence rate, increase the irregularity of the weights and threshold value, avoid BP neural network training into...
In this paper, a self-learning approach is proposed towards solving scene-specific pedestrian detection problem without any human annotation involved. The self-learning approach is deployed as progressive steps of object discovery, object enforcement, and label propagation. In the learning procedure, object locations in each frame are treated as latent variables that are solved with a progressive...
The Correlation Filter is an algorithm that trains a linear template to discriminate between images and their translations. It is well suited to object tracking because its formulation in the Fourier domain provides a fast solution, enabling the detector to be re-trained once per frame. Previous works that use the Correlation Filter, however, have adopted features that were either manually designed...
Recent advances in deep learning have shown exciting promise in filling large holes in natural images with semantically plausible and context aware details, impacting fundamental image manipulation tasks such as object removal. While these learning-based methods are significantly more effective in capturing high-level features than prior techniques, they can only handle very low-resolution inputs...
We consider learning a distance metric in a weakly supervised setting where bags (or sets) of instances are labeled with bags of labels. A general approach is to formulate the problem as a Multiple Instance Learning (MIL) problem where the metric is learned so that the distances between instances inferred to be similar are smaller than the distances between instances inferred to be dissimilar. Classic...
In linear representation-based image classification, an unlabeled sample is represented by the entire training set. To obtain a stable and discriminative solution, regularization on the vector of representation coefficients is necessary. For example, the representation in sparse representation-based classification (SRC) uses L1 norm penalty as regularization, which is equal to lasso. However, lasso...
Given a state-of-the-art deep neural network classifier, we show the existence of a universal (image-agnostic) and very small perturbation vector that causes natural images to be misclassified with high probability. We propose a systematic algorithm for computing universal perturbations, and show that state-of-the-art deep neural networks are highly vulnerable to such perturbations, albeit being quasi-imperceptible...
The past few years have seen a dramatic increase in the performance of recognition systems thanks to the introduction of deep networks for representation learning. However, the mathematical reasons for this success remain elusive. A key issue is that the neural network training problem is nonconvex, hence optimization algorithms may not return a global minima. This paper provides sufficient conditions...
Deep learning methods achieve great success recently on many computer vision problems. In spite of these practical successes, optimization of deep networks remains an active topic in deep learning research. In this work, we focus on investigation of the network solution properties that can potentially lead to good performance. Our research is inspired by theoretical and empirical results that use...
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.