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.
Large and sparse datasets with a lot of missing values are common in the big data era. Naive Bayes is a good classification algorithm for such datasets, as its time and space complexity scales well with the size of non-missing values. However, several important questions about the behavior of naive Bayes are yet to be answered. For example, how different mechanisms of missing, data sparseness and...
In this paper, we study how to initialize the convolutional neural network (CNN) model for training on a small dataset. Specially, we try to extract discriminative filters from the pre-trained model for a target task. On the basis of relative entropy and linear reconstruction, two methods, Minimum Entropy Loss (MEL) and Minimum Reconstruction Error (MRE), are proposed. The CNN models initialized by...
This paper is based on feed forward neural network (FFNN) optimization by particle swarm intelligence (PSI) used at the starting point of neural network for initial guess to weights and biases. Once the weights and biases are found, the same are used to train the neural network for prediction and classification benchmark problems. Further the trained neural network is the used to predict future sample...
Predicting ad click-through rates is the core problem in display advertising, which has received much attention from the machine learning community in recent years. In this paper, we present an online learning algorithm for click-though rate prediction, namely Follow-The-Regularized-Factorized-Leader (FTRFL), which incorporates the Follow-The-Regularized-Leader (FTRL-Proximal) algorithm with per-coordinate...
Matrix factorisation (MF), an effective recommendation algorithm, predicts user preferences on items based on the historical preferences of other like-minded users. Classical MF methods do not explicitly distinguish the significances across the underlying factors that determine a users' preference on an item. The identical contribution of latent factors during learning results unnecessary updates...
Article is devoted to the problems of building simulation models which enhance the methods of learning processes. Majority of the educational systems provide education personalization, creating adapting ways to learning, whereas one of the most important components of specialist competency is efficient interoperability. In this connection dynamic education environment and system design task is considered...
As an advanced artificial intelligence technology, error back-propagation (BP) neural network algorithm has been widely applied to electronics, communications, automation and other fields. However, traditional BP neural network algorithm has the disadvantages, such as inclination to stick into local optima, and slow convergence, which exert a great impact on the processing performance, and also limit...
In order to achieve the fast classification for Ultra-low-frequency (ULF) electron field data in the Space, this paper designs an electric field classifier based on the back-propagation (BP) neural network with extracting the ULF section electric field waveform data of the Wenchuan earthquake, using the statistical methods to obtain four characteristics of the mean value, mean square error, skewness...
Gait as a biometric feature that can be measured remotely without physical contact and proximal sensing has attract significant attention. This paper proposes to use con-volutional neural networks (ConvNets) and multi-task learning model(MLT) to identify human gait and to predict multiple human attributes simultaneously. In comparison to previous approaches, two novelty in our convolutional approach...
Millimeter wave (mmWave) communication is a promising candidate for future extremely high data rate, wireless networks. The main challenges of mmWave communications are deafness (misalignment between the beams of the transmitter and receiver) and blockage (severe attenuation due to obstacles). Due to deafness, prior to link establishment between a client and its access point, a time consuming alignment/beam...
A bidirectional blind equalization based on the constant modulus algorithm (CMA) and subspace-based algorithm (SBA) is proposed in this paper. Without any training sequence or channel estimation, blind equalization improves the transmission efficiency significantly in underwater acoustic communications. The combining scheme in which two outputs run in opposite directions exploits the diversity and...
Deep CCA is a recently proposed deep neural network extension to the traditional canonical correlation analysis (CCA), and has been successful for multi-view representation learning in several domains. However, stochastic optimization of the deep CCA objective is not straightforward, because it does not decouple over training examples. Previous optimizers for deep CCA are either batch-based algorithms...
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...
In this paper, Fuzzy Neural Network (FNN) is transformed into an equivalent Fully Connected Neuro-Fuzzy Inference System (F-CONFIS). The F-CONFIS is a new type of neural network that differs from traditional neural networks, which there are the dependent and repeated weights. For these special properties, its learning algorithm should be different from that of the conventional neural networks. Therefore,...
Enterprise in financial trouble is a comprehensive event and the enterprise financial situation can be reflected through the liquidity ratio, earnings per share and net assets per share and cash content per share. Artificial neural network method is used to establish the financial early warning model to find the potential financial crisis at an early age. The experiment results show that BP neural...
This paper briefly discusses the basic principle of artificial neural network. BP network model based on time series has been established through an instance. Training and testing have been done for the network using existing observation data. Compared with the measured value through regression analysis, the effectiveness and accuracy of the network have been proved. It can be a prediction method...
Convolutional Neural Network (CNN) is a type of feed-forward artificial neural network, exploiting the unknown structure in input distribution to discover good representations with multiple layers of small neuron collections. CNN uses relatively little pre-processing compared to other classification algorithms, usually uses gradient decent to updates the parameters in the network. Since CNN was introduced...
Support vector machine has obtained more and more attentions as a new method of machine learning based on the statistic learning theory. At the same time, there are increasing concerns about the fault diagnosis for practical engineering systems. Firstly, many kinds of SVM algorithms will be introduced, such as LS-SVM, LSVM and PSVM and so on. Besides, the advantages and disadvantage of those methods...
Most state-of-the-art solutions for localizing facial feature landmarks build on the recent success of the cascaded regression framework [7, 15, 34], which progressively predicts the shape update based on the previous shape estimate and its feature calculation.
The jamming attack is one of the most severe threats in cognitive radio networks, because it can lead to network degradation and even denial of service. However, a cognitive radio can exploit its ability of dynamic spectrum access and its learning capabilities to avoid jammed channels. In this paper, we study how Q-learning can be used to learn the jammer strategy in order to pro-actively avoid jammed...
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.