In speech recognition, discriminative training has proved to be an effective method to improve recognition accuracy. It has successfully improved systems of different scales and different languages. While discriminative training has been developing for over 20 years, it continues to draw attention to researchers and remains to be one of the most important topics in speech recognition to date. D...

One important factor in cardiac rehabilitation and training is the correct analysis of aerobic and anaerobic thresholds for individual training plans. Several published algorithms produce exact results within a very homogeneous group of subjects (similar age, weight and level of fitness). We implemented these algorithms and evaluated their accuracy against data of a heterogeneous group of subje...

The objective of this research was to determine the best model and compare performances in terms of producing landuse maps from six supervised classification algorithms. As a result, different algorithms such as the minimum distance ofmean (MDM), Mahalanobis distance (MD), maximum likelihood (ML), artificial neural network (ANN), spectral anglemapper (SAM), and support vector machine (SVM) were...

Recurrent Neural Networks (RNNs) are powerful models that achieve unparalleled performance on several pattern recognition problems. However, training of RNNs is a computationally difficult task owing to the well-known “vanishing/exploding” gradient problems. In recent years, several algorithms have been proposed for training RNNs. These algorithms either: exploit no (or limited) curvature infor...

Problem statement: Constructive neural network learning algorithms provide optimal ways to determine the architecture of a multi layer perceptron network along with learning algorithms for determining appropriate weights for pattern classification problems. These algorithms initially start with small network and dynamically allow the network to grow by adding and training neurons as needed unti...

Hidden Markov models (HMMs) are powerful statistical tools for biological sequence analysis. Many recently developed Bioinformatics applications employ variants of HMMs to analyze diverse types of biological data. It is typically fairly easy to design the states and the topological structure of an HMM. However, it can be difficult to estimate parameter values which yield a good prediction perfo...

Currently, deep neural networks are deployed on low-power portable devices by first training a full-precision model using powerful hardware, and then deriving a corresponding lowprecision model for efficient inference on such systems. However, training models directly with coarsely quantized weights is a key step towards learning on embedded platforms that have limited computing resources, memo...

This article proposes offline language-free writer identification based on speeded-up robust features (SURF), goes through training, enrollment, and identification stages. In all stages, an isotropic Box filter is first used to segment the handwritten text image into word regions (WRs). Then, the SURF descriptors (SUDs) of word region and the corresponding scales and orientations (SOs) are extr...

The classification problem derived from information extraction (IE) has an imbalanced training set. This is particularly true when learning from smaller datasets which often have a few positive training examples and many negative ones. This paper takes two popular IE algorithms – SVM and Perceptron – and demonstrates how the introduction of an uneven margins parameter can improve the results on...