Search

Machine learning and pattern recognition techniques have been successfullyapplied to algorithmic problems in free groups. In this paper, we seek toextend these techniques to finitely presented non-free groups, with aparticular emphasis on polycyclic and metabelian groups that are of interest tonon...

We propose to focus on the problem of discovering neural networkarchitectures efficient both in terms of prediction quality and cost. Forinstance, our approach is able to solve the following tasks: 'learn a neuralnetwork able to predict well in less than 100 milliseconds' or 'learn anefficient model...

The ability to automatically detect certain types of cells or cellularsubunits in microscopy images is of significant interest to a wide range ofbiomedical research and clinical practices. Cell detection methods have evolvedfrom employing hand-crafted features to deep learning-based techniques...

Data streams typically have items of large number of dimensions. We study thefundamental heavy-hitters problem in this setting. Formally, the data streamconsists of $d$-dimensional items $x_1,\ldots,x_m \in [n]^d$. A $k$-dimensionalsubcube $T$ is a subset of distinct coordinates $\{ T_1,\cdots,T_k \...

Recent advances in deep learning for tomographic reconstructions have showngreat potential to create accurate and high quality images with a considerablespeed-up. In this work we present a deep neural network that is specificallydesigned to provide high resolution 3D images from restricted...

Homography estimation between multiple aerial images can provide relativepose estimation for collaborative autonomous exploration and monitoring. Theusage on a robotic system requires a fast and robust homography estimationalgorithm. In this study, we propose an unsupervised learning algorithm...

Lifelong machine learning methods acquire knowledge over a series ofconsecutive tasks, continually building upon their experience. Current lifelonglearning algorithms rely upon a single learning agent that has centralizedaccess to all data. In this paper, we extend the idea of lifelong learning...

This paper considers a class of reinforcement-based learning (namely,perturbed learning automata) and provides a stochastic-stability analysis inrepeatedly-played, positive-utility, strategic-form games. Prior work in thisclass of learning dynamics primarily analyzes asymptotic convergence...

We propose a novel monocular visual odometry (VO) system called UnDeepVO inthis paper. UnDeepVO is able to estimate the 6-DoF pose of a monocular cameraand the depth of its view by using deep neural networks. There are two salientfeatures of the proposed UnDeepVO: one is the unsupervised deep...

Recurrent neural networks (RNNs) are state-of-the-art in voiceawareness/understanding and speech recognition. On-device computation of RNNson low-power mobile and wearable devices would be key to applications such aszero-latency voice-based human-machine interfaces. Here we present Chipmunk, asmall...

The persistence of racial inequality in the U.S. labor market against ageneral backdrop of formal equality of opportunity is a troubling phenomenonthat has significant ramifications on the design of hiring policies. In thispaper, we show that current group disparate outcomes may be immovable even...

Cloud users (clients) with limited storage capacity at their end canoutsource bulk data to the cloud storage server. A client can later access herdata by downloading the required data files. However, a large fraction of thedata files the client outsources to the server is often archival in nature...

In a multi-unit market, a seller brings multiple units of a good and tries tosell them to a set of buyers that have monetary endowments. While a Walrasianequilibrium does not always exist in this model, natural relaxations of theconcept that retain its desirable fairness properties do exist.We study...

We show that the (stochastic) gradient descent algorithm provides an implicitregularization effect in the learning of over-parameterized matrixfactorization models and one-hidden-layer neural networks with quadraticactivations. Concretely, we show that given $\tilde{O}(dr^{2})$ random...

Intelligent Transportation Systems (ITSs) providing vehicle-relatedstatistical data are one of the key components for future smart cities. In thiscontext, knowledge about the current traffic flow is used for travel timereduction and proactive jam avoidance by intelligent traffic controlmechanisms...

Parity games have important practical applications in formal verification andsynthesis, especially to solve the model-checking problem of the modalmu-calculus. They are also interesting from the theory perspective, as they arewidely believed to admit a polynomial solution, but so far no such...

We formulate the abnormal event detection problem as an outlier detectiontask and we propose a two-stage algorithm based on k-means clustering andone-class Support Vector Machines (SVM) to eliminate outliers. After extractingmotion features from the training video containing only normal events, we...

The goal of computational color constancy is to preserve the perceptivecolors of objects under different lighting conditions by removing the effect ofcolor casts caused by the scene's illumination. With the rapid development ofdeep learning based techniques, significant progress has been made in...

Hate speech, offensive language, sexism, racism and other types of abusivebehavior have become a common phenomenon in many online social media platforms.In recent years, such diverse abusive behaviors have been manifesting withincreased frequency and levels of intensity. This is due to the openness...

In recent years, offensive, abusive and hateful language, sexism, racism andother types of aggressive and cyberbullying behavior have been manifesting withincreased frequency, and in many online social media platforms. In fact, pastscientific work focused on studying these forms in popular media...