Transfer Learning for Human & AI

A fundamental problem is to specify which agents are responsible for the joint outcome of their behaviors and to which extent . We model multi-agent interaction as an extensive form game of imperfect information . Forward responsibility identifies responsibility of a group of agents for an outcome along all possible plays, whereas backwardresponsibility identifies responsibility along a given play .…

All known algorithms need at least $Omega(m)$ communication for coloring and MIS . We study the communication cost (or message complexity) of these problems . We ask: Can we solve problems such as coloringand MIS using sublinear, i.e., $o(m), communication, and if so under whatconditions?…

This paper presents an efficient solution to the loadbalancing problem in such systems that improves on and overcomes problems of previous solutions . The load balancing problem is formulated as a stochasticoptimization problem . The resulting dispatching policy can be computed very efficiently, making the solution practically viable .…

Solving the CDG problem is a key part of the designand verification process for new electronic circuits, including the chips that power modern servers and smartphones . We show that combining implicitfiltering (IF), an existing derivative free optimization (DFO) method, with adeep neural network global approximator leads to an accelerated DFO method .…

Federated learning (FL) is a privacy-preserving machine learning method . It is proposed to allow training of models using data from many different clients, without these clients having to transfer all their data to a centralserver . FL models trained using the high-volume clients can perform similarly to a centrally-trained model, though there is much more noise in results than would typically be expected for acentrally-trained models .…

Aimsun, SymuVia, Vissim, SUMO are currently available for traffic impact assessment of new technologies such as truckplatooning . The same simulation studies can be performed in different simulation software . We designed a cross-platform architecture for simulating a truck platooning functionality using software from different software .…

Previous studies played an audio adversarial example as a digital signal to perform physical attacks, which would be easily rejected by audio replay detection modules . In the physical experiment, we achieved targeted attacks with success rate of 100%, while the word error rate (WER) on speech recognition was only increased by 3.55% .…

The XCycles BackProjection model (XCBP), incontrast to the feedforward model approach, fully uses the iterative correctionprocedure in each cycle to reconstruct the residual error correction for theencoded features in both low- and high-resolution space . The proposed approach showed high outperformance compared to theclassical interpolation operators and to the recent feedforward state-of-the-art models .…

This paper focuses on how data centers can usetheir geographic load flexibility to reduce carbon emissions through cleverinteractions with electricity markets . Because electricity market clearingaccounts for congestion and power flow physics in the electric grid, the carbonemissions associated with electricity use varies between (potentiallygeographically close) locations .…

This paper considers an enhancement of the classical iterated penalty Picard(IPP) method for the incompressible Navier-Stokes equations . Anderson acceleration (AA) is used to significantly improve its convergence properties . IPP enhanced with AA improves its linear convergence rate by the gain factor associated with the underlying optimization problem .…

Deep neural networks such as BERT have made great progress in relationclassification . But it is still a question of concern whether these models recognize the directionality ofrelations . To explore thequestion, a novel evaluation task, called Relation Direction Recognition (RDR) is proposed .…

G-View can judiciously generate a view set from a query workload by exploring the graph properties of candidate views and considering their efficacy . The tool then selects the views using a graph gene algorithm (GGA), which relies on athree-phase framework that explores graph view transformations to reduce the view space and optimize the view benefit .…

Researchers suggest that similar to 5G, 6G technology must be human-centric where high secrecy together with high datarate will be the key features . These challenges can be easily overcomeutilizing PHY security techniques over high-frequency free-space or underwateroptical wireless communication (UOWC) technologies .…

Skin contraction is an important biophysical process that takes place duringand after the recovery of deep tissue injury . This process is mainly caused by fibroblasts (skin cells) thatexert pulling forces on the surrounding extracellular matrix (ECM) Modelling is done in multiple scales: agent-based modelling on the microscale and continuum-based .…

Numerical approximation of the Boltzmann equation presents a challenging problem due to its high-dimensional, nonlinear, and nonlocal collision operator . The Petrov-Galerkin spectral method uses Chebyshev functions to achieve desired convergence and conservation properties . We demonstrate the superior accuracy of the proposed method in comparison to the Fourier spectral method with the help of the then-uniform fast Fourier transform (NuffT) The basis functions (bothtest and trial functions) are carefully chosen to be carefully chosen .…

Automatic Essay Scoring (AES) is defined as the computer technology that evaluates and scores the written essays . In order to bridge this gap, we create a large corpus with several essays written by Brazilian high school students on an online platform .…

We discuss a pointwise numerical differentiation formula on multivariatescattered data . The formula is based on the coefficients of local polynomial interpolation atDiscrete Leja Points . Error bounds and sensitivity estimates to perturbations are provided . Several numerical tests are presented to show the accuracy of the approximation of partial derivatives of any order compatible with thefunction regularity .…

Hypersequent GV (HGV) is a modular and extensible corecalculus for functional programming with session types that enjoy deadlockfreedom, confluence, and strong normalisation . HGV exploits hyper-environments, which are collections of type environments, to ensure that structuralcongruence is type preserving . As a consequence we obtain a tight operationalcorrespondence between HGV and HCP, a hypersequent-based process-calculusinterpretation of classical linear logic .…

The coupling between cell-free massive multiple-input multiple- input multiple-output (MIMO) systems and usermobility is considered in this paper . Three beamforming techniques are proposed in the considered scenario, along with a dynamic user association technique (handover) Numerical results reveal that the proposed beamforming and userassociation techniques are effective in a considered scenario .…

Data compression is widely used in contemporary column-oriented DBMSes . Pioneering systems have introduced compression to tackle the disk bandwidth bottleneck by trading CPU power for it . The main issue of this is a trade-off between the compression ratio and the decompression CPU cost .…

A reconfigurable intelligent surface (RIS) is a flat layer made ofsub-wavelength-sized reflective elements capable of adding a tunable phaseshift to the impinging electromagnetic wave . This paper considers the fundamental problem of target detection in a RIS-aided multiple-inputmultiple-output (MIMO) radar system .…

We study two classes of summary-based cardinality estimators that usestatistics about input relations and small-size joins . We model these estimators as picking bottom-to-top paths in acardinality estimation graph . We show that on a largesuite of datasets and workloads, the accuracy of such estimates is up to threeorders of magnitude more accurate in mean q-error than some prior heuristicsthat have been proposed in prior work .…

In this paper, the role of secret key with finite rate is studied to enhancethe secrecy performance of the system when users are operating in interferencelimited scenarios . To address this problem, a 2-user Gaussian Z-IC with secrecyconstraint at the receiver is considered .…

In active Visual-SLAM, a robot relies on the information retrieved by its cameras to control its own movements for autonomous mapping of the environment . We obtain more accurate maps, with lower energy consumption, while maintaining the benefits of the active approach with respect to the baseline .…

In this paper, we consider a UAV-enabled MEC platform that serves multiple mobile ground users with random movements and task arrivals . We aim to minimizethe average weighted energy consumption of all users subject to the average UAVenergy consumption and data queue stability constraints .…

Computer aided Tabular Data Extraction has always been a very challenging and error prone task because it demands both Spectral and Spatial Sanity of data . We discuss a novel approach using Computer Vision for extraction of tabular data from images or vectorpdf(s) converted to image(s).…

A Data Ecosystem offers a keystone-player or alliance-driven infrastructure that enables the interaction of different stakeholders and the resolution of interoperability issues among shared data . Despite years of research, trustability is still affected by the absence of transparent and traceable data-driven pipelines .…

Researchers analyzed communication behavior of 866 managers, out of which 111 left a large service company . Findings show managers who quit had lower closeness centrality and less engaged conversations . Researchers say managers who chose to quit tended to shift their communication behavior starting from 5 months before leaving, by increasing their degree, the complexity of their language, as well as their oscillations in betweenness centrality, and the number of “nudges” they need to send to peers before getting an answer .…

Casson fluid flow model tightly coupled with variable coefficients ADR ($VADR$) equation . Casson viscositycoefficient is taken to be dependent upon solute mass concentration . This paper presents the stability and convergence analyses of the stabilized finiteelement solution . The proposed expressions of the stabilization parameters help in obtaining optimal order of convergences .…

We develop an approach to choice principles and their contrapositivebar-induction principles as extensionality schemes . We introduce, for a domain A, a codomainB and a “filter” T on finite approximations of functions from A to B, ageneralised form GDC(A,B,T) of the axiom of dependent choice and bar induction principle GBI(A) such that: .…

We curated WikiPII, an automatically labeled dataset composed of Wikipediabiography pages, annotated for personal information extraction . Although automatic annotation can lead to a high degree of label noise, it is aninexpensive process and can generate large volumes of annotated documents .…

In recent times, we have seen an increased use of text chat for communication on social networks and smartphones . This particularly involves the use ofHindi-English code-mixed text which contains words which are not recognized in English vocabulary . We have worked on detecting emotions in these mixed dataand classify the sentences in human emotions which are angry, fear, happy or sad .…

Dynamic and non-linear systems are emerging as potential candidates forrandom bit generation . This paper introduces a newcontinuous chaotic system along with its corresponding implementation, which targets field-programmable gate array (FPGA) This chaotic system has fivedimensions, which exhibit complex chaotic dynamics, thus enabling theutilization of chaotic signals in cryptography .…

This paper introduces an algorithm to perform optimal reorientation of aspacecraft during a high speed flyby mission that maximizes the time a certain target is kept within the field of view of scientific instruments . The method handles the nonlinear dynamics of the spacecraft, sun exclusionconstraint, torque and momentum limits on the reaction wheels as well as potential faults in these actuators .…

CoTexT is a transformer-based architecture encoder-decoder model that learns the representative context between naturallanguage (NL) and programming language (PL) through multi-task learning . It achieves state-of-the-art on all downstream tasks such as code summarizing/documentation, codegeneration, defect detection, code debugging, etc. We evaluate multi-tasks on different generation and classification tasks on CodeXGLUE and it achieves state of the art on alldownstream tasks .…

This paper introduces our system at NLPTEA-2020 Task: Chinese GrammaticalError Diagnosis (CGED) CGED aims to diagnose four types of grammatical errors which are missing words (M), redundant words (R), bad word selection (S) anddisordered words (W) The automatic CGED system contains two parts including error detection and error correction and our system is designed to solve the error detection problem .…

Machine learning and data mining techniques are effective tools to classify large amounts of data . But they tend to preserve any inherent bias in the data,for example, with regards to gender or race . Removing such bias from data or the learned representations is quite challenging .…

In this paper, we use a model of large random network game to explore the conditions under which the Nash equilibrium (NE) of the game is affected by a perturbation . We use a phase transition phenomenon observed in finite rankdeformations of large .…

QuatDE is anovel model with a dynamic mapping strategy to explicitly capture avariety of relational patterns . The mapping strategy dynamically selects the transitionvectors associated with each triplet, used to adjust the point position of theentity embedding vectors in the quaternion space via Hamilton product .…

Faults in photovoltaic (PV) systems can seriously affect the efficiency, energy yield as well as the security of the entire PV plant . Fault diagnosis of PV arrays is indispensable for improving the reliability, efficiency, productivity and safety of PV powerstations .…

Sketch-based conditions can effectively describe the geometry of faces, including contours of facial components, hairstructures, as well as salient edges (e.g., wrinkles) on face surfaces . However, existing disentangling methods are not optimized for human face editing, and cannotachieve fine control of facial details such as wrinkles .…

Analyzing structural properties of social networks has many applications . However, these applications are not supported by federated social networks that allow users to store their social links locally on their end devices . The private hierarchical clustertrees enable a service provider to query the community structure around a user at various granularities without the users having to share their raw contact information .…

We derive low-order, inf-sup stable and divergence-free finite element approximations for the Stokes problem using Worsey-Farin splits in threedimensions and Powell-Sabin splits in two dimensions . The velocity space simplyconsists of continuous, piecewise linear polynomials, where as the pressurespace is a subspace of piecewise constants with weak continuity properties atsingular edges (3D)…

We evolve PyDTNN, a framework for distributed parallel training of DeepNeural Networks, into an efficient inference tool for convolutionalneural networks . Ourexperiments evaluate both inference throughput (measured in processed images/s) and inference latency (i.e., time-to-response) when varying the level of thread parallelism and the processor powermodes .…

Speech Emotion Recognition systems are currently available in only a few languages, including English,German, and Italian . In this paper, we present SEMOUR, the first scripteddatabase of emotion-tagged speech in the Urdu language, to design an UrduSpeech Recognition System . On a random testsample, our model correctly predicts an emotion with a state-of-the-art 92% accuracy .…

Reversible computing is a computational paradigm in which computations are deterministic in both the forward and backward direction . We investigate the formalsemantics of the reversible functional programming language Rfun . We introduce join inverse rig categories, the natural marriage of joininverse categories and rig categories .…

A novel speaker diarization method called End-to-End-Neural-Diarization-vector clustering (EEND- vector clustering) was onlyevaluated so far on simulated 2-speaker meeting-like data . The proposed method combines advantages of bothframeworks, i.e. high performance and handling of overlapped speechbased on EEND, and robust handling of long recordings with an arbitrary number of speakers based on clustering-based approaches .…

Multilingual neural machine translation aims at learning a single translation model for multiple languages . LaSS learns LanguageSpecific Sub-network (LaSS) for each language pair to counter parameter interference . The LaSS obtains gains on 36 language pairs by up to 1.2 BLEU .…

The FRaGenLP algorithm forgenerating random linear programming problems of large dimension $n$ on clustercomputing systems . The algorithm uses two likeness metrics toprevent the addition of a new random inequality that is similar to one already present in the constraint system .…