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.
Artificial neural networks (ANN) are among the nonlinear prediction techniques popular in the last two decades. Recent studies show that ANN can be modeled with different training techniques. ANN is usually trained by the backpropagation method (BP). In this study, ANN structures were trained by using artificial bee colony algorithm (ABC) and, weight and bias values were tried to be determined. ABC...
Deep Neural Networks (DNN) are the dominant technique widely used in English and Chinese speech recognition currently. However, Tibetan speech recognition research starts late and mainly uses Hidden Markov Model (HMM). In this paper, We show a better method of replacing Gaussian Mixture Models (GMM) by DNN to Tibetan Lhasa dialect speech recognition system. The system contains seven layers of features...
This paper presents a novel method for fault detection and location in modular five-level converters (MFLC) based on stacked sparse autoencoder (SSAE). SSAE is composed of multiple SAE and a softmax classifier. The capacitor voltage signals of all sub-modules (SMs) in the MFLC circuit are combined into a multi-channel signal. By moving window along the multi-channel signal, a set of signal segments...
In this paper, a text independent speaker recognition system based on Gaussian mixture models (GMM) was developed with a specific focus on the use of a voice activated detector (VAD) algorithm in the training and testing. At the training level, a modified estimation/maximization (EM) algorithm is used. It is less prone to get trapped around a local maximum and so, it will have more chance to converge...
The success of deep learning in vision can be attributed to: (a) models with high capacity; (b) increased computational power; and (c) availability of large-scale labeled data. Since 2012, there have been significant advances in representation capabilities of the models and computational capabilities of GPUs. But the size of the biggest dataset has surprisingly remained constant. What will happen...
Data diversity in terms of types, styles, as well as radiometric, exposure and texture conditions widely exists in training and test data of vision applications. However, learning in traditional neural networks (NNs) only tries to find a model with fixed parameters that optimize the average behavior over all inputs, without using data-specific properties. In this paper, we develop a meta-level NN...
Advances in modeling and knowledge representation, data mining, semantic Internet, analytical methods and open data are the basis for new models of knowledge analysis. The growth of information and data exceeds the ability of organizations to analyze them. This problem is particularly expressed in terms of knowledge and learning processes. Analytical methods can be successfully applied in studying...
The method of approximating a discriminant functions of the training set is proposed. The sign of the discriminant functions allows us to classify the point in one or another class. The approximation is constructed with greater precision in the neighborhood of zero values of the discriminant function. To estimate a posterior probability of a class of a point two methods are proposed: based on a series...
In this paper, a reinforcement learning approach is proposed to detect unexpected faults, where the noise-to-signal ratio of the data series is minimized for achieving robustness. The model parameter is taken as a special action of the reinforcement learning, and the policy valuation and policy improvement are utilized to find the parameters, which can make the estimated model consistent to the real-time...
A large portion of data mining and analytic services use modern machine learning techniques, such as deep learning. The state-of-the-art results by deep learning come at the price of an intensive use of computing resources. The leading frameworks (e.g., TensorFlow) are executed on GPUs or on high-end servers in datacenters. On the other end, there is a proliferation of personal devices with possibly...
Deep neural networks have been widely applied in the field of environmental sound classification. However, due to the scarcity of carefully labeled data, their training process suffers from over-fitting. Data augmentation is a technique that alleviates this issue. It augments the training set with synthetic data that are created by modifying some parameters of the real data. However, not all kinds...
Anomaly detection is the process of identifying unusual signals in a set of observations. This is a vital task in a variety of fields including cybersecurity and the battlefield. In many scenarios, observations are gathered from a set of distributed mobile or small form factor devices. Traditionally, the observations are sent to centralized servers where large-scale systems perform analytics on the...
In order to solve the problem of lacking shear wave velocity information in oil and gas field, based on conventional logging data, a support vector machine(SVM) model is used to map the relationship between shear wave velocity and natural gamma, acoustic time difference and resistivity of shale, and then a machine learning method for shear wave velocity prediction is proposed. The model was trained...
Sparse Modeling Representative Selection (SMRS) has been recently proposed for finding the most relevant instances in datasets. This method deploys a data self-representativeness coding in order to infer a coding matrix that is regularized with a row sparsity constraint. The method assumes that the score of any sample is set to the L2 norm of the corresponding row in the coding matrix. Since the SMRS...
The fuzzy restricted Boltzmann machine (FRBM) is demonstrated to have better generative and discriminative capabilities than traditional RBM. We now further investigate and compare the generative ability of DBN with FRBM on image reconstruction. The DBN is pre-trained by stacking RBMs layer by layer and then fine-tuned by the wake-sleep algorithm. Then the FRBM, RBM and DBN are compared in detail...
Dropout is a technique widely used for preventing overfitting while training deep neural networks. However, applying dropout to a neural network typically increases the training time. This paper proposes a different dropout approach called controlled dropout that improves training speed by dropping units in a column-wise or row-wise manner on the matrices. In controlled dropout, a network is trained...
We present a neural network technique for the analysis and extrapolation of time-series data called Neural Decomposition (ND). Units with a sinusoidal activation function are used to perform a Fourier-like decomposition of training samples into a sum of sinusoids, augmented by units with nonperiodic activation functions to capture linear trends and other nonperiodic components. We show how careful...
Machine learning has become one of the go-to methods for solving problems in the field of networking. This development is driven by data availability in large-scale networks and the commodification of machine learning frameworks. While this makes it easier for researchers to implement and deploy machine learning solutions on networks quickly, there are a number of vital factors to account for when...
There has been a phenomenal increase in the utility of text classification (TC) in applications like targeted advertisement and sentiment analysis. Most applications demand that the model be efficient and robust, yet produce accurate categorizations. This is quite challenging as their is a dearth of labelled training data because it requires assigning labels after reading the whole document. Secondly,...
Deep learning has been proposed for soft sensor modeling in process industries. However, conventional deep neural network (DNN) is a static network and thereby can not embrace evident dynamics in processes. Motivated by nonlinear autoregressive with exogenous input (NARX) model and neural nets based dynamic modeling, a dynamic network called NARX-DNN is put forward by further utilizing historical...
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.