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.
We propose EC3, a novel algorithm that merges classification and clustering together in order to support both binary and multi-class classification. EC3 is based on a principled combination of multiple classification and multiple clustering methods using a convex optimization function. We additionally propose iEC3, a variant of EC3 that handles imbalanced training data. We perform an extensive experimental...
The success of deep neural networks usually relies on a large number of labeled training samples, which unfortunately are not easy to obtain in practice. Unsupervised domain adaptation focuses on the problem where there is no labeled data in the target domain. In this paper, we propose a novel deep unsupervised domain adaptation method that learns transferable features. Different from most existing...
One of the most current challenging problems in Gaussian process regression (GPR) is to handle large-scale datasets and to accommodate an online learning setting where data arrive irregularly on the fly. In this paper, we introduce a novel online Gaussian process model that could scale with massive datasets. Our approach is formulated based on alternative representation of the Gaussian process under...
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...
Estimating depth from a single RGB image is an ill-posed and inherently ambiguous problem. State-of-the-art deep learning methods can now estimate accurate 2D depth maps, but when the maps are projected into 3D, they lack local detail and are often highly distorted. We propose a fast-to-train two-streamed CNN that predicts depth and depth gradients, which are then fused together into an accurate and...
Training deep neural networks is difficult for the pathological curvature problem. Re-parameterization is an effective way to relieve the problem by learning the curvature approximately or constraining the solutions of weights with good properties for optimization. This paper proposes to reparameterize the input weight of each neuron in deep neural networks by normalizing it with zero-mean and unit-norm,...
Deep learning methods achieve great success recently on many computer vision problems. In spite of these practical successes, optimization of deep networks remains an active topic in deep learning research. In this work, we focus on investigation of the network solution properties that can potentially lead to good performance. Our research is inspired by theoretical and empirical results that use...
Support vector machine (SVM) is a popular machine learning method and has been widely applied in many real-world applications. Since SVM is sensitive to noises, fuzzy SVM (FSVM) has been proposed to relieve the over-fitting problem caused by noises through assigning a fuzzy membership to each sample. Then, different samples make different contributions to the learning of classification hyperplane...
In the last few years, geometric semantic genetic programming has incremented its popularity, obtaining interesting results on several real life applications. Nevertheless, the large size of the solutions generated by geometric semantic genetic programming is still an issue, in particular for those applications in which reading and interpreting the final solution is desirable. In this paper, we introduce...
The problem of assessing the level of competence of students as a result of studying individual courses of the program in the process of instruction is considered, taking into account the vagueness of the formulation of competences as learning objectives and the evaluation of the learning outcomes of disciplines.
We propose a sequential algorithm for learning sparse radial basis approximations for streaming data. The initial phase of the algorithm formulates the RBF training as a convex optimization problem with an objective function on the expansion weights while the data fitting problem imposed only as an ℓ∞-norm constraint. Each new data point observed is tested for feasibility, i.e., whether the data fitting...
This paper extends the idea of Universum learning to regression problems. We propose new Universum-SVM formulation for regression problems that incorporates a priori knowledge in the form of additional data samples. These additional data samples, or Universum samples, belong to the same application domain as the training samples, but they follow a different distribution. Several empirical comparisons...
Objectives: Nowadays breath test, using the Ghoss method for the calculation of gastric emptying of solids, is characterized by a very high number of expirations in a very long time (about 4 hours). In this work, a simplified model aiming to the reduction of the number of expirations during this time was designed, preserving high levels of accuracy, sensitivity and specificity in the classification...
This work presents methods to automatically find optimal parameter settings for convolutional neural networks (CNNs) by using an evolutionary algorithm called particle swarm optimization (PSO). Even though the parameter space is extremely large (> 10 20), we experimentally show that a better parameter setting can be found for Alexnet configuration for five different image datasets. We have also...
The use of deep neural networks (DNNs) for feature extraction and Gaussian mixture models (GMMs) for acoustic modelling is often termed a tandem system configuration and can be viewed as a Gaussian mixture density neural network (MDNN). Compared to the direct use of DNN output probabilities in the acoustic model, the tandem approach suffers from a major weakness in that the feature extraction stage...
The ability to grasp ordinary and potentially never-seen objects is an important task in both domestic and industrial robotics. For a system to accomplish this, it must autonomously identify grasping locations by using information from various sensors, such as Microsoft Kinect 3D camera. Despite numerous progress, significant work still remains to be done for this task. To this effect, we propose...
The P300 Speller is a Brain Computer Interface that enables communication using the EEG signal. The P300 wave is an Event Related Potential that occurs as a response to a familiar stimulus. This system can be used to aid persons who are unable to communicate via conventional methods. In this paper, the P300 Speller has been modified to allow communication in three languages: English, Sinhala and Tamil...
Retrieving a small set of relevant and interesting objects from a large background class is challenging because classifiers can easily be overwhelmed by the large class. Classifiers have been developed that are more sensitive to the small class, and typically they optimize a ranking, or precision at the top. These measures can be costly because they often look at pairwise rankings. The classical approach...
Domain adaptation methods can be highly sensitive to class balance, particularly the usually unknown balance of the unlabeled test set. In this work, we analyze the effect of imbalance on a well-known algorithm, ARTL (Adaptation Regularization Transfer Learning) and propose four approaches for mitigating the adverse effects of imbalance. These include (1) balancing the training set for pseudo-label...
The F-measure and its variants are performance measures of choice for evaluating classification and retrieval tasks in the presence of severe class imbalance. It is thus highly desirable to be able to directly optimize these performance measures on large-scale data. Recent advances have shown that this is possible in the simple binary classification setting. However, scant progress exists in multiclass...
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.