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.
Word2Vec is a popular set of machine learning algorithms that use a neural network to generate dense vector representations of words. These vectors have proven to be useful in a variety of machine learning tasks. In this work, we propose new methods to increase the speed of the Word2Vec skip gram with hierarchical softmax architecture on multi-core shared memory CPU systems, and on modern NVIDIA GPUs...
Multi-view learning is a novel paradigm that aims at obtaining better results by examining the information from several perspectives instead of by analysing the same information from a single viewpoint. The multi-view methodology has widely been used for semi-supervised learning, where just some patterns were previously classified by an expert and there is a large amount of unlabelled ones. However...
Data representation is a fundamental task in machine learning, which affects the performance of the whole machine learning system. In the past few years, with the rapid development of deep learning, the models for word embedding based on neural networks have brought new inspiration to the research of natural language processing. In this paper, two kinds of schemes for improving the Continuous Bag-of-Words...
Software development teams apply security practices to prevent vulnerabilities in the software they ship. However, vulnerabilities can be difficult to find, and security practices take time and effort. Stakeholders can better guide software development if they have empirical data on how security practices are applied by development teams. The goal of this paper is to inform managers and developers...
Recurrent neural networks are represented as non-linear models of dynamic systems. This kind of neural networks is divided into two groups, which are globally and locally recurrent neural networks. Some types are distinguished among globally recurrent networks. The major approximation properties and features of every distinguished type are emphasized. The represented analysis is useful for choosing...
Deductive logic and its variants enjoy the common property of monotonicity. For tasks such as inductive reasoning and belief revision, this was eventually deemed a serious flaw, prompting attempts to construct non-monotonic versions of logic. With the introduction of the idea of probabilistic reasoning to AI, particularly with the advent of Bayesian networks (BNs), the aforementioned monotonicity...
In recent years, there has been an increasing interest in music generation using machine learning techniques typically used for classification or regression tasks. This is a field still in its infancy, and most attempts are still characterized by the imposition of many restrictions to the music composition process in order to favor the creation of “interesting” outputs. Furthermore, and most importantly,...
Regression-based tasks have been the forerunner regarding the application of machine learning tools in the context of data mining. Problems related to price and stock prediction, selling estimation, and weather forecasting are commonly used as benchmarking for the comparison of regression techniques, just to name a few. Neural Networks, Decision Trees and Support Vector Machines are the most widely...
Neural machine translation (NMT) has shown promising results and rapidly gained adoption in many large-scale settings. With the NMT model being widely used in empirical productions, its long-standing weakness in handling the rare and out of vocabulary words has been amplified a lot. In order to release the model from the stress of “understanding” the rare words, copy mechanism has been proposed to...
Echo state networks are a recently developed type of recurrent neural network where the internal layer is fixed with random weights, and only the output layer is trained on specific data. Echo state networks are increasingly being used to process spatio-temporal data in real-world settings, including speech recognition, event detection, and robot control. A strength of echo state networks is the simple...
We develop T2API, a context-sensitive, graph-based statisticaltranslation approach that takes as input an English description of aprogramming task and synthesizes the corresponding API code templatefor the task. We train T2API to statistically learn the alignmentsbetween English and APIs and determine the relevant API elements. Thetraining is done on StackOverflow, which is a bilingual corpus onwhich...
Nowadays, developing effective techniques able to deal with data coming from structured domains is becoming crucial. In this context kernel methods are the state-of-the-art tool widely adopted in real-world applications that involve learning on structured data. Contrarily, when one has to deal with unstructured domains, deep learning methods represent a competitive, or even better, choice. In this...
Since the advent of the IoT era, various IoT devices have proliferated, transforming ordinary spaces into smart spaces such as smart home, smart office, and smart building. To provide user-friendly service to people, the majority of previous studies have focused on activity recognition and prediction in singleuser environments such as ambient assisted living (AAL) and activities of daily living (ADL)...
The current paper presents a novel recurrent neural network model, predictive multiple spatio-temporal scales RNN (P-MSTRNN), which can generate as well as recognize dynamic visual patterns in a predictive coding framework. The model is characterized by multiple spatio-temporal scales imposed on neural unit dynamics through which an adequate spatio-temporal hierarchy develops via learning from exemplars...
This paper presents a case study of a gamified learning experience, designed with a guiding gamification framework, for a software engineering study group. The group was formed to evaluate the learning experience in a laboratory-like setting, and the results are intended to inform the design process. Grounded-theory procedures were used to analyze qualitative data about students' perceptions of the...
The abstraction tasks are challenging for multi-modal sequences as they require a deeper semantic understanding and a novel text generation for the data. Although the recurrent neural networks (RNN) can be used to model the context of the time-sequences, in most cases the long-term dependencies of multi-modal data make the back-propagation through time training of RNN tend to vanish in the time domain...
Most work on tweet sentiment analysis is mono-lingual and the models that are generated by machine learning strategies do not generalize across multiple languages. Cross-language sentiment analysis is usually performed through machine translation approaches that translate a given source language into the target language of choice. Machine translation is expensive and the results that are provided...
Educational games have been used as an innovative instructional strategy in order to achieve learning more effectively in Software Engineering (SE) education. However, it is essential to systematically evaluate such games in order to obtain sound evidence on their benefits. And, although, several SE games have been evaluated adopting diverse research designs and measurements, so far no larger scale...
It is a great challenge to model and mine the e-commercial data, which is made up of multiple types of objects, such as products, users, comments and tags. To model the complicated interactive relationships in the the e-commercial data, we propose to transform the complex e-commercial data into a text-rich heterogeneous e-commercial network. Then three neural network based embedding algorithms named...
The complexity of contemporary external action missions is increasing with a growing number of civilian and other non-military actors operating in a shared environment. There are currently not sufficient capabilities for civil-military cooperation in place which hinders operational effectiveness and the full exploitation of the information sharing potential. We contribute to the assessment of information...
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.