Transfer Learning for Human & AI

We analyze the Fourier growth of various well-studied classes of “structured”$\mathbb{F}_2$-polynomials . This study is motivated by applications inpseudorandomness, in particular recent results and conjectures due to[CHHL19,CHLT19,CGLSS20] We show that any symmetric degree-$d$ $p$ has $L_1$ Fourier weight at level $k$ and this is tight for any constant $k$.…

Researchers propose novel shilling attack called Graph cOnvolution-based generativeshilling ATtack (GOAT) GOAT adopts the primitive attacks’ paradigm that assigns items for fake users by sampling . It deploys a generative adversarial network (GAN)that learns the real rating distribution to generate fake ratings .…

Automatic metrics are commonly used as the exclusive tool for declaring thesuperiority of one machine translation system’s quality over another . We investigate which metrics have the highest accuracy to makesystem-level quality rankings for pairs of systems . We show that the sole use of BLEUnegatively affected the past development of improved models.…

Causal relations (If A, then B) are prevalent in requirements artifacts . We lack an approach capable of extracting causal relations from natural language with reasonable performance . In this paper, wepresent our tool CATE (CAusality Tree Extractor), which is able to parse thecomposition of a causal relation as a tree structure .…

We envision robots that can collaborate and communicate seamlessly with humans . We introduce a new task,dialogue object search: A robot is tasked to search for a target object in a human environment while engaging in a “video call” with a remote human who has additional but inexact knowledge about the target’s location .…

In a self-interested setting, agents may strategically hide some connections to make themselves seem to be more important . In this paper, we study the incentive compatible (IC) selectionmechanism to prevent such manipulations . We propose the Geometric Mechanism, which selects an agent with at least 1/2 of the optimal progeny in expectation under the properties of incentive compatibility and fairness .…

The Social IoT paradigm enables access controlsystems to aggregate community context and sociability information from devicesto enhance robustness and security . NS-3 Simulations show the ELECTRONperformance under Sybil attacks on several IoT communities so that it has . detected more than 90% of attackers in a scenario with 150 nodes into .…

Current approaches are limited due to inadequate shapepriors and the insufficiency of the derived image observations for a reliable alignment with the 3D model . We introduce a subcategory-aware deformable vehicle model that makes use of aprediction of the vehicle type for a more appropriate regularisation of the shape .…

Researchers propose novel shilling attack called Graph cOnvolution-based generativeshilling ATtack (GOAT) GOAT adopts the primitive attacks’ paradigm that assigns items for fake users by sampling . It deploys a generative adversarial network (GAN)that learns the real rating distribution to generate fake ratings .…

We introduce Inayatullah’s Causal Layered Analysis (CLA) method from thefield of futures studies into the domain of design patterns . We develop a briefcase study that shows how we have integrated CLA with patterns in acollaborative research project studying the Emacs editor .…

The effectiveness of the code review is that it ensures the quality of software and makes it updated . Code review is the best process that helps the developers to develop asystem errorless . This report contains two different code review papers to beevaluated and find the influences that can affect the code reviewing process .…

Abstract reasoning, i.e., inferring complicated patterns from givenobservations, is a central building block of artificial general intelligence . We propose logic-guided generation (LoGe), a novelgenerative DNN framework that reduces abstract reasoning as an optimization problem in propositional logic . LoGe is composed of three steps: extractpropositional variables from images, reason the answer variables with a logiclayer, and reconstruct the answer image from the variables .…

The Public Good index is a power index for simple games introduced by Holler and Packel . Some authors also speak of the Holler–Packel index . Here we generalize the ideas to games with several levels of approval in the input and output .…

We consider a multiproduct monopoly pricing model . We provide sufficient conditions under which the optimal mechanism can be implemented via upgradepricing . The first set ofconditions is given by a weak version of monotonicity of types and virtualvalues . The second set of conditions establishes the optimality of upgrade pricing for type spaces withmonotone marginal rates of substitution .…

In this paper, we adapt to cell-free Massive MIMO (multiple-inputmultiple-output) the finite-blocklength framework introduced by \”Ostman et al. (2020) for the characterization of the packet error probability achievable with Massive MimO, in the ultra-reliable low-latency communications (URLLC) regime . By means of numerical simulations, we show that, toachieve the high reliability requirements in URLLC, MMSE signal processing must be used .…

Motivated by the need to provide differentiated quality-of-service (QoS) ingrant-free uplink transmissions in 5G networks and beyond, we extend theprobabilistic analysis of coded Poisson receivers (CPR) to the setting with multiple classes of users and receivers . For such a CPR system, we prove (undercertain technical conditions) that there is a region, called the stabilityregion in this paper .…

Maximally Recoverable (MR) TensorCodes, introduced by Gopalan et al., are tensor codes which can correct everyerasure pattern that is theoretically possible to correct . Tensor codes are useful in distributed storage because a single erasure can be correctedquickly either by reading its row or column .…

Survey presents an overview of eXplainableArtificial Intelligence (XAI) used in deep learning-based medical image analysis . Paper concludes with an outlook of future opportunities for XAI in medical imaging analysis . The call for explainability of XAI methods grows, especially in high-stakes decision-making areas such asmedical image analysis, says the survey .…

This paper studies a problem of jointly optimizing two important operations in mobile edge computing . The objective function includes both the costs of forwarding requests, processing requests, and reconfiguring edge servers . Simulation results show that our algorithms significantly outperform other state-of-the-art policies, including one that assumes the knowledge of all future request arrivals .…

Quantum computing promises to solve difficult optimization problems more efficiently than classical computers, but requires fault-tolerant quantum computers with millions of qubits . Hybrid algorithms combining classical and quantum computers are used to overcome errors introduced by today’s quantum computers .…

Artificial intelligence chatbots are the vanguard in technology-based intervention to change people’s behavior . To develop intervention chatbots, the first step is to understand natural language conversation strategies in humanconversation . This work lays the foundation for developing a personalized physical activity intervention bot .…

Time-series forecasting plays an important role in many domains, such as wind power, stock market fluctuations, or motor overheating . In some of these tasks, some particular moments often are underrepresented in thedataset, resulting in a problem known as imbalanced regression .…

Consider n nodes communicating over an unreliable broadcast channel . Each node has a single packet that needs to be communicated to all other nodes . Time is slotted, and a time slot is long enough for each node to broadcast one packet .…

Satellite networks are expected to support global connectivity and servicesvia future integrated 6G space-terrestrial networks . In the past few years, many such private constellations have been launched or are in planning, e.g.SpaceX and OneWeb to name a few . We show that the link capacity, delay, and handover rate vary across the constellation, so the optimal handover strategydepends on the constellation design .…

An ethical AI must be capable of inferring unspoken rules, interpreting nuance and context, possess and be able to infer intent, and explain not just its actions but its intent . It can learn what is meant by a sentence and infer the intent of others in terms of its own experiences .…

Language models (LMs) pretrained on a large text corpus and fine-tuned on a downstream task becomes a de factotraining strategy for several natural language processing (NLP) tasks . We propose aback-translated task-adaptive pretraining (BT-TAPT) method that increases the amount of task-specific data for LM re-pretraining by augmenting the task data .…

In this paper, we study the problem of sparse channel estimation via acollaborative and fully distributed approach . The estimation problem isformulated in the angular domain by exploiting the spatially common sparsitystructure of the involved channels in a multi-user scenario .…

Under assumptions about the data-generative process, the causal graph can often be identified up to anequivalence class . Proposing new realistic assumptions to circumscribe suchequivalence classes is an active field of research . In this work, we propose anew set of assumptions that constrain possible causal relationships based on the nature of the variables .…

We define cooperative games on general graphs and generalize Lloyd S.Shapley’s celebrated allocation formula for those games in terms of stochasticpath integral driven by the associated Markov chain on each graph . We then show that the value allocation operator, one for each player defined by thestochastic path integral, coincides with the player’s component game which is the solution to the least squares (or Poisson’s) equation .…

Measuring meaning is a central problem in cultural sociology and word embeddings may offer powerful new tools to do so . But like any tool, they buildon and exert theoretical assumptions . In certain ways, word embedding methods are vulnerable to the same, enduring critiques of these premises .…

In multi-dimensional time series analysis, a task is to conductevolutionary subspace clustering, aiming at clustering temporal data according to their evolving low-dimensional subspace structures . We demonstrate that this method can not onlyinterpolate data at any time step, but also achieve higher accuracy than other state-of-the-art evolutionarysubspace-cluing methods .…

The general adwords problem has remained largely unresolved . We define asubcase called $k-TYPICAL, $k \in \Zplus$ as follows: the total budgetof all the bidders is sufficient to buy $k$ bids for each bidder . We also giverandomized online algorithms for other special cases of adwords .…

We introduce a contractive abstract dynamic programming framework and relatedpolicy iteration algorithms . These algorithms are specifically designed for sequential zero-sumgames and minimax problems with a general structure . The advantage of our algorithms over alternatives is that they resolve some long-standing convergence difficulties of the “natural” policyiteration algorithm, which have been known since the Pollatschek and Avi-Itzhakmethod [PoA69] for finite-state Markov games .…

MFGNet aims to boost the message communication between visible and thermaldata by adaptively adjusting the convolutional kernels for various input images . To address issues caused by heavy occlusion, fast motion, and out-of-view, we propose to conduct a joint local and global search byexploiting a new direction-aware target-driven attention mechanism .…

The S.rensen–Dice Coefficient has recently seen rising popularity as aloss function (also known as Dice loss) due to its robustness in tasks where the number of negative samples significantly exceeds that of positive samples . Conventional training of polyphonic sound event detection systemswith binary cross-entropy loss often results in suboptimal detectionperformance as the training is often overwhelmed by updates from negativesamples .…

The ever-evolving internet of things (IoT) has led to the growth of numerous wireless sensors, communicating through the internet infrastructure . For extending the lifetime of thesesensors, radio frequency energy harvesting (RFEH) technology has proved to be promising . In this paper, we propose CURE, a novel framework for RFEH that combines the benefits of cell-free massive MIMO (CFmMIMO), unmannedaerial vehicles (UAVs), and reconfigurable intelligent surfaces (RISs) toprovide seamless energy harvesting to IoT devices .…

Maximally Recoverable (MR) TensorCodes, introduced by Gopalan et al., are tensor codes which can correct everyerasure pattern that is theoretically possible to correct . Tensor codes are useful in distributed storage because a single erasure can be correctedquickly either by reading its row or column .…

Re-identification (ReID) aims at matching objects in surveillance cameras with different viewpoints . But there is noprocessing method for the ReID task in multiple scenarios at this stage . The CPP is a method based on key point detection, usingcopy and paste, to composite a new semantic image dataset in two different semantic image datasets .…

The Social IoT paradigm enables access controlsystems to aggregate community context and sociability information from devicesto enhance robustness and security . NS-3 Simulations show the ELECTRONperformance under Sybil attacks on several IoT communities so that it has . detected more than 90% of attackers in a scenario with 150 nodes into .…

This paper specifies an extensive form as a 5-ary relation (i.e. set ofquintuples) which satisfies certain abstract axioms . Each quintuple is understood to list a player, a situation (e.g. information set), a decisionnode, a decision node, an action, and a successor node .…

To examine reproducibility of COVID-19 research, we create a dataset of pre-prints posted to arXiv, bioRxiv, medRxv, and SocArXiv . We extract the text from these pre-prints and parse them looking for keywords signalling theavailability of the data and code underpinning the pre-printed .…

Sound event localization and detection (SELD) aims to unify the tasks of sound event detection and direction-of-arrivalestimation . SELD inherits the challenges of both tasks, such as noise, reverberation, interference, polyphony, and non-stationarity of soundsources . Experimental results indicate polyphony as the main challenge in SELD, due to the difficulty in detecting all sound events of interest .…

Avirtual codeathon activity, as part of this learning scheme, was conducted for180 undergraduate students to focus on analysis and design of solutions to real-world problems in the Covid-19 pandemic situation . Activity-based learning helps students to learn through participation, AvVirtual Codeathon activity was conducted by students .…

Motivated by the need to provide differentiated quality-of-service (QoS) ingrant-free uplink transmissions in 5G networks and beyond, we extend theprobabilistic analysis of coded Poisson receivers (CPR) to the setting with multiple classes of users and receivers . For such a CPR system, we prove (undercertain technical conditions) that there is a region, called the stabilityregion in this paper .…

Guessing Random Additive Noise Decoding (GRAND) is a recently proposed method searching for the error pattern applied to the transmittedcodeword . We propose an improved error pattern schedule that can improve the performance ofORBGRAND of 0.5dB at a block error rate (BLER) of $10^{-5}$, with increasinggains as the BLER decreases .…

In this paper, a novel optimization model for joint beamforming and power control in the downlink (DL) of a cell-free massive MIMO (CFmMIMO) system is presented . The objective of the proposed optimization model is to minimize themaximum user interference while satisfying quality of service (QoS) constraints and power consumption limits .…

Measuring meaning is a central problem in cultural sociology and word embeddings may offer powerful new tools to do so . But like any tool, they buildon and exert theoretical assumptions . In certain ways, word embedding methods are vulnerable to the same, enduring critiques of these premises .…

Computational approaches have access to the information about thetypicality of entire events and situations described in language . The evaluation of these models was performed incomparison with SDM, a framework specifically designed to integrate events insentence meaning representations . Our results show that TLMs can reach performances that are comparable to those achieved by SDM .…

In this note we examine the autoregressive generalization of the FNetalgorithm . Self-attention layers from the standard Transformerarchitecture are substituted with a trivial sparse-uniformsampling procedure based on Fourier transforms . Using the Wikitext-103 benchmark, FNetAR retains state-of-the-art performance (25.8 ppl) on thetask of causal language modeling .…

Linear codes in projective space $mathbb{P}_q(n)$ were first considered by Braun,Etzion and Vardy . We establish that the normalizedminimum distance of a linear code is maximum if and only if it is equidistant . We prove that the upper bound on the size of such class of linear codes is $2^n$ when $q=2$ as conjectured by Braun et al.…