Transfer Learning for Human & AI

Reconfigurable intelligent surfaces (RISs) represent a new technology that can shape the radio wave propagation . We exploit the well-known duality between theGaussian multiple-input multiple- input multiple-output (MIMO) BC and multiple-access channel(MAC) We propose an alternating optimization (AO) algorithm which optimizes the users’ covariance matrices and the RIS phase shifts in the dual MAC .…

In swarm robotics, a set of robots has to perform a given task with specified capabilities (model) and under a given adversarial scheduler . In literature there are four main modelsof robots with lights: $LUMI, $FSTA, $FCOM, OBLOT, and $OBLOT$ .…

The standard procedure for computing the persistent homology of a filteredsimplicial complex is the matrix reduction algorithm . In practice, the quadratic scaling in the number oftranspositions often makes this maintenance procedure slower than simply computing the decomposition from scratch .…

Grid maps are widely established for the representation of static objects inrobotics and automotive applications . In this paper, we introduce new inverse radar sensor models covering radar sensor artifacts such as measurement ambiguities to integrate automotive radar sensors for improved velocity estimation .…

The general inverse kinematics (IK) problem of a manipulator plays a vital role in robotics modeling, planning and control . To efficiently solve the generalized IK, this paper proposes aninterval branch-and-bound-based approach, which is augmented with a fastnumerical IK-solver-enabled search heuristics .…

In this paper, we investigate the use of linguistically motivated andcomputationally efficient structured language models for reranking N-besthypotheses in a statistical machine translation system . These language models, developed from Constraint Dependency Grammar parses, tightly integrate knowledge of words, morphological and lexical features, and syntactic constraints .…

In this manuscript, we develop an efficient algorithm to evaluate theazimuthal Fourier components of the Green’s function for the Helmholtz equation in cylindrical coordinates . A computationally efficient algorithm is essential for solvers for electromagnetic scattering from bodies of revolution (e.g.,…

Software code complexity is a well-studied property to determine software component health . We propose a metric called mutant density where we use mutation as a method to introduce artificial faults in code, and count the number of possible mutations per line .…

The performance of projection-based model order reduction methods for solvingparameter-dependent systems of equations highly depends on the properties of the operator, which can be improved by preconditioning . The proposed approach involves heavy computations in bothoffline and online stages that are circumvented by random sketching.…

Robustness is a key concern for Rust library development because Rust promises no risks of undefined behaviors if developers use safe APIs only . We identify severalessential requirements for library fuzzing, including validity and effectiveness of fuzz targets, high API coverage, and efficiency .…

We present a new linearly implicit exponential integrator that preserves thepolynomial first integrals or Lyapunov functions for the conservative and dissipative stiff equations . The method is tested by bothoscillated ordinary differential equations and partial differential equations,e.g., an averaged system in wind-induced oscillation, the Fermi-Pasta-Ulams, and the polynomial pendulum oscillators .…

The bin-packing problem continues to remain relevant in numerous applicationareas . This technical report discusses the empirical performance of different heuristics for certain test problems .…

Galerkin variational integrators approximate avariational (Lagrangian) problem by restricting the space of curves to the set of polynomials of degree at most $s$ and approximating the action integral . We show that, if the quadrature rule is sufficiently accurate, the order of the integrators thus obtained is $2s$.…

Paper proposes unsupervised two-stage approach to discover intents and generate meaningful intent labels automatically from acollection of unlabeled utterances . In the first stage, we aim to generate semantically coherent clusters where the utterances within each clusterconvey the same intent .…

We follow up on the idea of Lars Arge to rephrase the Reduce and Applyalgorithms of Binary Decision Diagrams as iterative I/O-efficient algorithms . These algorithms are implemented in a new BDD library, named Adiar . For instances of about 50 GiB, our algorithms, using external memory, are only upto 3.9 times slower compared to Sylvan, exclusively using internal memory .…

We revisit the quantum algorithms for obtaining Forrelation [Aaronson etal, 2015] values . We evaluate some of the well-known cryptographicallysignificant spectra of Boolean functions . We use similar idea to obtain a technique in estimating thecross-correlation (and thus autocorrelation) value at any point, improving uponthe existing algorithms .…

Language models are ubiquitous in current NLP, and their multilingualcapacity has recently attracted considerable attention . XLM-T is a framework for using and evaluating multilingual language models in Twitter . This framework featurestwo main assets: (1) a strong multilingual baseline consisting of a model pre-trained on millions of tweets in over thirty languages .…

Research looked at 474 IBM Jazz practitioners assembled in 149 teams working on around 30,000 software development tasks over a three-year period . Results found that teams expressed different attitudes when working on various formsof software tasks, and they were particularly emotional when working to remedy bugs .…

This paper introduces a new method to stylize 3D geometry . The key observation is that the surface normal is an effective instrument to capturedifferent geometric styles . This formulation can deform a 3D shape intodifferent styles within a single framework .…

Research statement generation (RSG) task aims to summarize one’s researchachievements and help prepare a formal research statement . For this task, we construct an RSG dataset with 62 research statements and the corresponding 1,203 publications . We propose a practical RSG method which identifies arearcher’s research directions by topic modeling and clustering techniques .…

There have been increasing concerns about Artificial Intelligence due to its unfathomable potential power . Researchers proposed to develop socially responsible AI (SRAI) One of these approaches is causal learning (CL) We survey state-of-the-art methods of CL for SRAI . We begin by examining the seven CL tools to enhance the social responsibility of AI .…

DeepImpact is a new documentterm-weighting scheme suitable for efficient retrieval using a standardinverted index . Compared to existing methods, it improves impact-scoremodeling and tackles the vocabulary-mismatch problem . When deployed in a re-ranking scenario, it can reach the same effectiveness of state-of-the-art approaches with up to 5.1x speedup inefficiency .…

Different platforms for benchmarking optimization algorithms use different data models and formats, which drastically inhibits identification of relevant data sets, their interpretation, and their interoperability . We report in this paper on the development of such an ontology, which we nameOPTION (OPTImization algorithm benchmarking ONtology) Our ontology providesthe vocabulary needed for semantic annotation of the core entities involved inthe benchmarking process, such as algorithms, problems, and evaluationmeasures .…

The algorithm takes input from citizens and schedules the store’s time-slots based on their importance to visit the facility . We show that it reduces the socialcongestion significantly using users’ visit data from a store . The problem becomes NP-complete as soon as the multi-slot demands are indivisibleand provide a polynomial-time mechanism that is truthful, individuallyrational, and approximately optimal .…

Hand gesture is a new and promising interface for locomotion in virtualenvironments . Finger Distance gesture and the Finger Number gesture are very promising interfaces for virtual locomotion . FingerTapping gesture needs further improvements before it can be used for virtualwalking .…

This article addresses the possibility of supporting the construction of emotions in the participants of Interactive Digital Narratives (IDN) by means of colours . The article uses goal models for expressing protostories . The core of the article consists of the case study where two colour synes-thetes wereasked to choose colours for eight emotions .…

With the proliferation of edge smart devices and the Internet of Vehicles technologies, intelligent fatigue detection has become one of themost-used methods in our daily driving . To address these issues, we propose FedSup, a client-edge-cloud framework for privacy and efficient fatigue detection .…

Few-shot and one-shot learning have been the subject of active and intensive research in recent years . Theory is based on intrinsic properties of high-dimensional spaces . We show that if the ambient or latent decision space of a learning machine is sufficiently high .dimensional…

Sponsored search ads appear next to search results when people look for products and services on search engines . As the fundamental basis ofsearch ads, relevance modeling has attracted increasing attention due to thesignificant research challenges and tremendous practical value .…

Inverse Optimal Control (IOC) is to analyze an observed behavior which is assumed to be optimal with respect to an unknown cost function . The IOC method uses an iterative trajectoryoptimization process to infer cost function weightings consistent with those used to generate a single demonstrated optimal trial .…

DefOrmable Object Manipulation(G-DOOM) is a long-standing challenge in robotics . It aims to learn latent Graph dynamics for DefOratable Object Manipulations . We train the resulting graph dynamics model through contrastive learning in a high-fidelity simulator . We evaluate a set of challenging cloth and rope manipulation tasks and show that G-Doomperforms a state-of-the-art method .…

Traditionally, clustering algorithms focus on partitioning the data intogroups of similar instances . The similarity objective is notsufficient in applications where a fair-representation of the groups in termsof protected attributes like gender or race is required for each cluster . In many applications, to make the clusters useful for the end-user, abalanced cardinality among the clusters is required .…

Evolutionary algorithms (EAs) represent a valid tool to overcome this issue . Designing optimal soft modular robots is difficult, due to non-trivialinteractions between morphology and controller . ViE-NEAT shows comparable performance to MAP-Elites on goal reaching, although it does not exploit any map .…

A wide range of modern science and engineering applications are formulated as optimization problems with partial differential equations (PDEs) These PDE-constrained optimization problems are typically solved using a standard discretize-then-optimize approach . In many industry applicationsthat require high-resolution solutions, the discretized constraints can easilyhave millions or even billions of variables, making it very slow for the standard iterative optimizer to solve the exact gradients .…

Clustering-based CF methods can deal with data sparsity and scalability problems . However, most of them are applied to a single embedding space . We argue user-item interactions should be observed from multiple views and characterized in an adaptive way .…

The bug growth pattern prediction is a complicated, unrelieved task, which needs considerable attention . Advance knowledge of the likely number of bugs discovered in the software system helps software developers in designatingsufficient resources at a convenient time . We observe that LSTM is effective when considering long-runpredictions whereas Random Forest Regressor enriched by exogenous variables performs better for predicting bugs in the short term .…

RDMAbox is a set of low level RDMA opti-mizations that provide better performance than previous ap-proaches . The optimizations are packaged in easy-to-use ker-nel and userspace libraries and presented through simplenodelevel abstractions . The I/O mergequeue at the same time functions as a traffic regulator to enforce admissioncontrol and avoidoverloading the NIC .…

Anovel second order cone program (SOCP) based optimization formulation forevaluating a grasps’ ability to apply wrenches to generate a linear motionalong a given direction and/or an angular motion about the given direction . Key feature of our approach is that we can consider the effect of contact wrenches from any contact of the object with the environment .…

In the coming smart ocean era, reliable and efficient communications are crucial for promoting a variety of maritime activities . Current maritimecommunication networks (MCNs) mainly rely on marine satellites and on-shorebase stations . The former generally provides limited transmission rate, while the latter lacks wide-area coverage capability .…

Mexico has kept electronic records of all taxable transactions since 2014 . Anonymized data collected by the Mexican federal government comprises more than80 million contributors (individuals and companies) and almost 7 billion monthly invoices among contributors between January 2015 and December 2018 .…

Voice Conversion (VC) deals with conversion of vocal style of one speaker to another speaker while keeping the linguistic contentsunchanged . VC task is performed through a three-stage pipeline consisting of speech analysis, speech feature mapping, and speech reconstruction . ALGAN-VC framework consists of some approaches to improve speech quality and voice similarity between source and target speakers .…

This paper presents a new approach for offensive language and hate speechdetection on social media . Our approach incorporates an offensive lexiconcomposed by implicit and explicit offensive and swearing expressions annotated with binary classes: context-dependent offensive and context-independentoffensive . Due to the severity of the hate speech and offensive comments inBrazil and the lack of research in Portuguese, Brazilian Portuguese is thelanguage used to validate our method .…

Reconfigurable intelligent surface (RIS) has shown promise in providing apparent benefits in wireless communication and positioning . Each labeled path contains spatial knowledge between the RISand the receiver, thus opening the door for sensing the surrounding world byRISs . The critical challenge is how the labeled paths can be extracted and distinguish from other paths, especially with multipath effects .…

The confirmation bias theory has indicated that a user is more likely to spread a piece of fake news when it confirms his/her existing beliefs/preferences . Users’ historical, socialengagements such as posts provide rich information about users’ preferencestoward news . We propose a new framework, UPFD, which captures various signals from user preferences by jointcontent and graph modeling .…

We give algorithms for computing coresets for clustering of polygonal curves and point sets . The size of the coreset is independent of the number of inputcurves/point sets to be clustered . We characterize a general condition on the restricted space of clustercenters .…

In data center, unexpected downtime caused by memory failures can lead to a decline in the stability of the server and even the entire information technology infrastructure . The single model we proposed won the top 15th inthe 2nd Alibaba Cloud AIOps Competition belonging to the 25th Pacific-AsiaConference on Knowledge Discovery and Data Mining .…

Regshock is a practical visual analytical approach to support the exploration and evaluation of financial regulation measurements . It is the first practical systemic method for the financial network intervention and risk mitigation problem . Regshock’s validated approach potentially improves the risk management and control capabilities of financial experts, authors say .…

Subjective self-reports in VR user studies is a burdening and often tedioustask for the participants . To minimize the disruption with the ongoingexperience VR research has started to administer the surveying directly insidethe virtual environments . However, due to the tedious nature of text-entry inVR, most VR surveying tools focus on closed questions with predetermined answers, while open questions with free-text responses remain unexplored .…

Math expressions are important parts of scientific and educational documents . But constructing textual descriptions for mathexpressions is nontrivial . In this paper, we explore the feasibility toautomatically construct descriptions for math expressions . We propose a hybrid model (MathDes) which consists of two important modules: Selector and Summarizer .…