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.
Automatic Term Extraction is an important issue in Natural Language Processing. This paper presents a new approach of terminology extraction combining with machine learning based on cascaded conditional random fields and corpus-based statistical model. In this approach, firstly, the low-layer and high-layer conditional random fields (CRFs) are used to extract the simple and compound terminologies...
In this work, we used single electrooculogram (EOG) signal to perform automatic sleep scoring. Deep belief network (DBN) and combination of DBN and Hidden Markov Models (HMM) are employed to discriminate sleep stages. Under the leave-one-out protocol, the average accuracy of DBN and DBN-HMM are 77.7% and 83.3% for all sleep stages, respectively. On the other hand, we found the EOG signal not only...
This paper explores the theory of learning with similarity functions in the context of common-sense reasoning and natural language processing. Based on this theory, the proposed approach (called Sim-Predictor) is characterized by the process of remapping the input space into a new space which is able to convey the similarity between the input pattern and a number of landmarks, i.e., a subset of patterns...
We propose a parallel training framework of convolutional neural networks (CNNs) for small sample learning. In the framework we model the feature filter process and show Sadowsky energy distribution exists in the model. Using Sadowsky energy distribution, the weights in convolutional kernels can be rearranged after each update according to special cases. With this rearrangement, each CNNs in the framework...
We propose an optimization method for belief propagation. First we mathematically show that the belief propagation algorithm can be optimized by imposing a reasonable restriction on the conditional probability tables in a Bayesian network. Then we demonstrate the efficiency of the proposed algorithm with experiments. Compared to the previously derived approximate algorithm, the proposed algorithm...
This paper presents a novel dimensionality reduction method, called uncorrelated transferable feature extraction (UTFE), for signal classification in brain-computer interfaces (BCIs). Considering the difference between the source and target distributions of signals from different subjects, we construct an optimization objective that finds a projection matrix to transform the original data in a high-dimensional...
This paper presents the design and simulation results of a silicon cochlea system that has closely similar behavior as the real cochlea. A cochlea filter-bank based on the improved three-stage filter cascade structure is used to model the frequency decomposition function of the basilar membrane; a filter tuning block is designed to model the adaptive response of the cochlea; besides, an asynchronous...
Ensemble learning of neural network is a learning paradigm where ensembles of several neural networks show improved generalization capabilities that outperform those of single networks. For deep learning of multi-layer neural networks, ensemble learning is still applicable. In addition, characteristics of deep neural networks can provide potential opportunities to improve the performance of traditional...
Similarity learning ranges over an extensive field in machine learning and pattern recognition. This paper deals with similarity learning based on multiple support vector data description (SVDD). It is well known that SVDD was proposed for one-class or two-class unbalanced learning problems. Thus, we propose a multiple SVDD (MSVDD) algorithm and apply it to multi-class learning problems. A SVDD model...
In this paper, we propose a novel subspace learning algorithm, termed as null space based discriminant sparse representation large margin (NDSLM). There are two contributions in the paper. First, we propose a new expectation to obtain the neighborhood information for large margin subspace learning, i.e., the within-neighborhood scatter and betweenneighborhood scatter are modeled by the sparse reconstruction...
Neural gas (NG) is a robust vector quantization algorithm for which a descriptive mathematical model is known. According to this model, the output configuration produced by the NG algorithm samples the input data distribution with a density that follows a power law with a magnification factor that depends on data dimensionality only. The effects of shape in the input data distribution on the NG behavior,...
In this paper we develop a whole set of parallel algorithms for improving the computation efficiency of a neurodynamic optimization (NDO) system proposed in our previous work recently. The NDO method is able to solve the sparse signal recovery problems in compressive sensing with the globally convergent optimal solution approximating to the L0 norm minimization, but has the shortcoming with heavy...
Feature selection and taking into account dynamic environments are two important aspects of modern data analysis and machine learning. In particular, performing feature selection on datasets where the latest instances contain more features than the initial ones is a problem that may be encountered in many application areas where new sensors are acquired. This paper proposes a method for incremental...
In this paper, we investigate the problem of music classification when training data is distributed throughout a network of interconnected agents (e.g. computers, or mobile devices), and it is available in a sequential stream. Under the considered setting, the task is for all the nodes, after receiving any new chunk of training data, to agree on a single classifier in a decentralized fashion, without...
The aim of collaborative clustering is to reveal the common underlying structures found by different algorithms while analyzing data. The fundamental concept of collaboration is that the clustering algorithms operate locally but collaborate by exchanging information about the local structures found by each algorithm. In this framework, the one purpose of this article is to introduce a new method which...
Robust appearance-based person re-identification can only be achieved by combining multiple diverse features describing the subject. Since individual features perform different, it is not trivial to combine them. Often this problem is bypassed by concatenating all feature vectors and learning a distance metric for the combined feature vector. However, to perform well, metric learning approaches need...
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.