Browse Proceedings

Occam’s razor is the principle stating that, all else being equal, simpler explanations for a set of observations are to be preferred to more complex ones. This idea can be made precise in the context of statistical inference, where the same ...

We explore competitive Hebbian learning strategies to train feature detectors in Convolutional Neural Networks (CNNs), without supervision. We consider variants of the Winner-Takes-All (WTA) strategy explored in previous works, i.e. k-WTA, e-soft-...

Understanding how to satisfy searchers’ information need (IN) is the main goal of Information Retrieval (IR) systems. In this study, we investigate the relationships between information need and the two key concepts of relevance and satisfaction ...

Machine learning is rapidly becoming one of the most important technology for malware traffic detection, since the continuous evolution of malware requires a constant adaptation and the ability to generalize [20]. However, network traffic datasets ...

In this work, we processed sets of images obtained by the light-sheet fluorescence microscopy method. We selected different cell groups and determined areas occupied by ensembles of cell groups in mouse brain tissue. Recognition of mouse neuronal ...

Fitting models with high predictive accuracy that include all relevant but no irrelevant or redundant features is a challenging task on data sets with similar (e.g. highly correlated) features. We propose the approach of tuning the hyperparameters ...

This paper investigates relevant features for the prediction of intraday S&P 500 returns. In contrast to most previous research, the problem is approached as a four class classification problem to account for the magnitude of the returns and not ...$\mathrm{}$$\mathrm{}$

Studies involving image colourisation have been garnering researchers’ keen attention over time, assisted by significant advances in various Machine Learning techniques and compute power availability. Traditionally, image colourisation has been an ...

In this short paper, a matrix perturbation bound on the eigenvalues found by principal component analysis is investigated, for the case in which the data matrix on which principal component analysis is performed is a convex combination of two data ...

Finding well-defined clusters in data represents a fundamental challenge for many data-driven applications, and largely depends on good data representation. Drawing on literature regarding representation learning, studies suggest that one key ...

We consider a context where (a) statistician publishes results of his study for a hypothesis testing problem, and (b) an observer with a full prior distribution reads the results. The observer may agree or disagree with the results, based on his ...

The process of industrial design engineering is often involved with the simultaneous optimization of multiple expensive objectives. The surrogate assisted multi-objective S-Metric Selection – Efficient Global Optimization (SMS-EGO) algorithm is ...

Traditional grid network has played a major role in society by distributing and transmitting electric supply to consumers. However, with the advancement in technology in Industry 4.0 has evolved the role of the Smart Grid (SG) network. SG network ...

Convolutional Neural Networks (CNNs) achieve state-of-the-art results in many application areas, including image classification. For some applications it would be useful but impractical to deploy them on mobile devices with limited memory and ...

Despite several rounds of institutional reform starting from 2005, the public procurement process in Russia remains marred by low competitiveness and inefficiency. In the years 2014–2018, almost half of the studied auctions failed to attract more ...

Autonomous driving is one of the most challenging problems of the last decades. The development in recent years is mainly due to the continuous expansion of Artificial Intelligence. Nowadays, most self-driving systems use Deep Learning techniques. ...

Model explainability, interpretability, and explainable AI have become major research topics, particularly for deep neural networks where it is unclear what features the network may have used to come to a particular output. This paper presents a ...

Text classification is the most basic Natural Language Processing (NLP) task. It has a wide range of applications ranging from sentiment analysis to topic classification. Recently, deep learning approaches based on Convolutional Neural Network (...

Time-series forecasting plays an important role in many domains. Boosted by the advances in Deep Learning algorithms, it has for instance been used to predict wind power for eolic energy production, stock market fluctuations, or motor overheating. ...

While reinforcement learning (RL) has proven to be the approach of choice for tackling many complex problems, it remains challenging to develop and deploy RL agents in real-life scenarios successfully. This paper presents pH-RL (personalization in ...

In the domain of hard real-time systems, the Worst-Case Execution Time (WCET) is one of the most important design criteria. Safely and accurately estimating the WCET during a static WCET analysis is computationally demanding because of the ...

In case only a limited amount of data is available, deep learning models often do not generalize well. We propose a novel deep learning architecture to deal with this problem and achieve high prediction accuracy. To this end, we combine four ...

Measuring the informational content of text in economic and financial news is useful for market participants to adjust their perception and expectations on the dynamics of financial markets. In this work, we adopt a neural machine translation and ...

Predicting high-quality images that depend on past images and external events is a challenge in computer vision. Prior proposals have tried to solve this problem; however, their architectures are complex, unstable, or difficult to train. This ...

The particle-in-cell numerical method of plasma physics balances a trade-off between computational cost and intrinsic noise. Inference on data produced by these simulations generally consists of binning the data to recover the particle ...

In this paper, a system for recognizing aerial survey images for finding and locating objects is proposed and constructed. This system includes the following blocks: input of area information, processing of aerial survey images, installation of ...

When people try to understand nuanced language they typically process multiple input sensor modalities to complete this cognitive task. It turns out the human brain has even a specialized neuron formation, called sagittal stratum, to help us ...

Machine Learning (ML) tasks, especially Computer Vision (CV) ones, have greatly progressed after the introduction of Deep Neural Networks. Analyzing the performance of deep models is an open issue, addressed with techniques that inspect the ...