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.
Restricted Boltzmann Machine (RBM) is a particular type of random neural network models modeling vector data based on the assumption of Bernoulli distribution. For multidimensional and non-binary data, it is necessary to vectorize and discretize the information in order to apply the conventional RBM. It is well-known that vectorization would destroy internal structure of data, and the binary units...
A proper strategy to alleviate overfitting is critical to a deep neural network (DNN). In this paper, we introduce the cross-loss-function regularization for boosting the generalization capability of the DNN, which results in the multi-loss regularized DNN (ML-DNN) framework. For a particular learning task, e.g., image classification, only a single-loss function is used for all previous DNNs, and...
Restricted Boltzmann Machine (RBM) is an important generative model modeling vectorial data. While applying an RBM in practice to images, the data have to be vectorized. This results in high-dimensional data and valuable spatial information has got lost in vectorization. In this paper, a Matrix-Variate Restricted Boltzmann Machine (MVRBM) model is proposed by generalizing the classic RBM to explicitly...
Monitoring of rock fragmentation is a commercially important problem for the mining industry. Existing analysis methods either resort to physically sieving rock samples, or using image analysis software. The currently available software systems for this problem typically work with 2D images and often require a significant amount of time by skilled human operators, particularly to accurately delineate...
Classical regression methods take vectors as covariates and estimate the corresponding vectors of regression parameters. When addressing regression problems on covariates of more complex form such as multi-dimensional arrays (i.e. Tensors), traditional computational models can be severely compromised by ultrahigh dimensionality as well as complex structure. By exploiting the special structure of tensor...
A compressive light field camera architecture has been proposed to recover light fields from a single image. This technique has recently gained increasing interest. The reconstruction quality of light field depends on the incoherence of a projection matrix and dictionary. Compressive light field acquisition is different from acquiring traditional signal while the projection matrix has specific structural...
Image segmentation seeks to partition the pixels in images into distinct regions to assist other image processing functions such as object recognition. Over the last few years dictionary learning methods have become very popular for image processing tasks such as denoising, and recently structured low rank dictionary learning has been shown to be capable of promising results for recognition tasks...
Image super-resolution means forming high-resolution images from low-resolution images. In this paper, we develop a new approach based on the deep Restricted Boltzmann Machines (RBM) for image super-resolution. The RBM architecture has ability of learning a set of visual patterns, called dictionary elements from a set of training images. The learned dictionary will be then used to synthesize high...
This paper proposes a method for supervised classification using Low-Rank Representation of transposed data. Recent papers have suggested that low rank representation of transposed data may be useful for feature extraction. We develop an algorithm called TLRRC for supervised classification using transposed data and demonstrate that its performance is competitive with state-of-the-art classification...
Learning from Demonstration (LfD) is a method of teaching an agent a task by a number of suitable demonstrations. The agent will then perform the task without any further supervision. In this paper, Discrete Hidden Markov Model (DHMM) is applied to train a robot for a mining inspection task. An initial training method based on the Gaussian Mixture Model (GMM) was developed and is compared to DHMM...
The chordiogram has recently been proposed for detection and segmentation of shapes in images. This paper evaluates the effectiveness of using chordiograms for recognizing hand written characters using the MNIST dataset. The method calculates a feature for each digit based on the geometric relationships of boundary pixels. The resultant features are used to train a support vector machine which is...
Current research for Learning From Demonstration (LfD) seems to concentrate on the learning kernel. This paper outlines the need for a more useful variable selection technique using the training dataset. The paper presents a new training dataset selection method, called Information Extraction (IE). The application area is a complex task involving robot mining tunnel inspection, and IE is applied to...
The Markov model has been applied to many prediction applications including the student models of intelligent tutoring systems. In this paper, we extend this well-known model to the weighted Markov model, and then apply it to student models in order to predict student behaviors. The prediction using our models is based not only on the frequency of collective behaviors of previous users, but also on...
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.