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.
Gatys et al. recently introduced a neural algorithm that renders a content image in the style of another image, achieving so-called style transfer. However, their framework requires a slow iterative optimization process, which limits its practical application. Fast approximations with feed-forward neural networks have been proposed to speed up neural style transfer. Unfortunately, the speed improvement...
We describe a method to produce a network where current methods such as DeepFool have great difficulty producing adversarial samples. Our construction suggests some insights into how deep networks work. We provide a reasonable analyses that our construction is difficult to defeat, and show experimentally that our method is hard to defeat with both Type I and Type II attacks using several standard...
Texture classification has been extensively studied in computer vision. Recent research shows that the combination of Fisher vector (FV) encoding and convolutional neural network (CNN) provides significant improvement in texture classification over the previous feature representation methods. However, by truncating the CNN model at the last convolutional layer, the CNN-based FV descriptors would not...
A popular approach to training classifiers of new image classes is to use lower levels of a pre-trained feed-forward neural network and retrain only the top. Thus, most layers simply serve as highly nonlinear feature extractors. While these features were found useful for classifying a variety of scenes and objects, previous work also demonstrated unusual levels of sensitivity to the input especially...
In this paper, a multi — factor prediction model based on Radical Basis Function(RBF) neural network is proposed to accurately predict the temperature of rolling bearing. According to the factors that affect the rolling bearing, including load, speed, vibration, displacement, bearing temperature and ambient temperature, the working temperature of the rolling bearing is predicted by combining the historical...
The performance of deep convolution neural networks will be further enhanced with the expansion of the training data set. For the image classification tasks, it is necessary to expand the insufficient training image samples through various data augmentation methods. This paper explores the impact of various data augmentation methods on image classification tasks with deep convolution Neural network,...
Deep learning has greatly improved visual recognition in recent years. However, recent research has shown that there exist many adversarial examples that can negatively impact the performance of such an architecture. This paper focuses on detecting those adversarial examples by analyzing whether they come from the same distribution as the normal examples. Instead of directly training a deep neural...
The problem of transferring a deep convolutional network trained for object recognition to the task of scene image classification is considered. An embedded implementation of the recently proposed mixture of factor analyzers Fisher vector (MFA-FV) is proposed. This enables the design of a network architecture, the MFAFVNet, that can be trained in an end to end manner. The new architecture involves...
Semi-supervised learning (SSL) is an import paradigm to make full use of a large amount of unlabeled data in machine learning. A bottleneck of SSL is the overfitting problem when training over the limited labeled data, especially on a complex model like a deep neural network. To get around this bottleneck, we propose a bio-inspired SSL framework on deep neural network, namely Deep Growing Learning...
We study unsupervised learning by developing a generative model built from progressively learned deep convolutional neural networks. The resulting generator is additionally a discriminator, capable of "introspection" in a sense — being able to self-evaluate the difference between its generated samples and the given training data. Through repeated discriminative learning, desirable properties...
Recently, the community of style transfer is trying to incorporate semantic information into traditional system. This practice achieves better perceptual results by transferring the style between semantically-corresponding regions. Yet, few efforts are invested to address the computation bottleneck of back-propagation. In this paper, we propose a new framework for fast semantic style transfer. Our...
This paper proposes a novel approach for segmenting primary video objects by using Complementary Convolutional Neural Networks (CCNN) and neighborhood reversible flow. The proposed approach first pre-trains CCNN on massive images with manually annotated salient objects in an end-to-end manner, and the trained CCNN has two separate branches that simultaneously handle two complementary tasks, i.e.,...
Scale recovery is one of the central problems for monocular visual odometry. Normally, road plane and camera height are specified as reference to recover the scale. The performances of these methods depend on the plane recognition and height measurement of camera. In this work, we propose a novel method to recover the scale by incorporating the depths estimated from images using deep convolutional...
In this paper, we propose an integrated system for scale-variance pedestrian detection. It consists of two cascaded components: a multi-layer detection neural network (MLDNN) for scale-variance pedestrian detection, and a fast decision forest (FDF) for boosting detection performance with only a slight decrease in speed. Experimental results on the Caltech Pedestrian dataset show that our approach...
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...
This work presents a method of classification of text documents using deep neural network with LSTM (long short-term memory) units. We have tested different approaches to build feature vectors, which represent documents to be classified: we used feature vectors constructed as sequences of words included in the documents, or, alternatively, we first converted words into vector representations using...
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...
This paper summarizes the AAIA'17 Data Mining Challenge: Helping AI to Play Hearthstone which was held between March 23, and May 15, 2017 at the Knowledge Pit platform. We briefly describe the scope and background of this competition in the context of a more general project related to the development of an AI engine for video games, called Grail. We also discuss the outcomes of this challenge and...
In this article, the problem of determining the significance of data features is considered. For this purpose the algorithm is proposed, which with the use of Sobol method, provides the global sensitivity indices. On the basis of these indices, the aggregated sensitivity coefficients are determined which are used to indicate significant features. Using such an information, the process of features'...
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.