Contrastive learning (CL) has recently emerged as an effective approach to learning representation in a range of downstream tasks . Central to this approach is the selection of positive (similar) and negative (dissimilar) setsto provide the model the opportunity to `contrast’ between data and classrepresentation in the latent space .…
The emergence of visual semantics through communication games
In this work, we consider a signalling gamesetting in which a `sender’ agent must communicate the information about animage to a `receiver’ who must select the correct image from many distractors . We investigate the effect of the feature extractor’s weights and of the task being solved on the visual semantics learned by the models .…
GP Context free Grammar Pre training for Text to SQL Parsers
A new method for Text-to-SQL parsing, Grammar Pre-training (GP) is proposed to decode deep relations between question and database . A random value is added behind a questionword which is recognized as a column, and the new sentence serves as the model input .…
Spectral Leakage and Rethinking the Kernel Size in CNNs
Convolutional layers in CNNs implement linear filters which decompose the input into different frequency bands . We show that the small size of CNN kernels make them susceptible to spectral leakage . To address this issue, we propose theuse of larger kernel sizes along with the Hamming window function to alleviateleakage in CNN architectures .…
Weakly Supervised Learning for Facial Behavior Analysis A Review
In recent years, there has been a shift in facial behavior analysis from the laboratory-controlled conditions to the challenging in-the-wild conditions due to superior performance of deep learning based approaches for many realworld applications . Labeling process of huge training data demands lot of human support with strong domainexpertise for facial expressions or action units, which is difficult to obtainin real-time environments .…
Parametric Rectified Power Sigmoid Units Learning Nonlinear Neural Transfer Analytical Forms
The paper proposes representation functionals in a dual paradigm where learning jointly concerns both linear convolutional weights and parametricforms of nonlinear activation functions . The nonlinear forms proposed forperforming the functional representation are associated with a new class ofparametric neural transfer functions called rectified power sigmoid units .…
GRADE AO Towards Near Optimal Spatially Coupled Codes With High Memories
Spatially-coupled (SC) codes are known for their threshold saturation phenomenon and low-latency windowed decoding algorithms . They also find application in various data storage systems because of their excellent performance . SC codes are constructed by partitioning an underlying block code, followed by rearranging andconcatenating the partitioned components in a “convolutional” manner .…
From Model driven to Data driven A Survey on Active Deep Learning
Active Deep Learning (ADL) only if its predictor is deep model, where the basic learner is called as predictorand the labeling schemes is called selector . With the development of deeplearning, the selector in ADL also is experiencing the stage from model-driven to data-driven .…
Approximate Integrals Over Bounded Volumes with Smooth Boundaries
A Radial Basis Function Generated Finite-Differences (RBF-FD) inspiredtechnique for evaluating definite integrals over bounded volumes that havesmooth boundaries in three dimensions is described . The proposed algorithm computes quadrature weights for $N$arbitrarily scattered nodes in only $O(N\mbox{ log}N)$ operations with highorders of accuracy .…
Asymptotic Assessment of Distribution Voltage Profile Using a Nonlinear ODE Model
This paper addresses the assessment problem in aframework of nonlinear differential equations . It provides a mathematically-rigor andquantitative method for assessing how the charging/discharging of EVs affectsthe spatial profile of distribution voltage . Effectiveness of the asymptotic charcterisation of solutions of the problem is established with simulations of both simple and practicalconfigurations of the power distribution grid .…
A Review of Graph Neural Networks and Their Applications in Power Systems
Deep neural networks have revolutionized many machine learning tasks in powersystems . Increasing number of applications in power systems where data are collected from non-Euclidean domains . Complexity of graph-structured data has brought significant challenges to the existing deep neural networks defined in Euclidean domain .…
Learning From Revisions Quality Assessment of Claims in Argumentation at Scale
Assessing the quality of arguments and of the claims the arguments are composed of has become a key task in computational argumentation . However, even if different claims share the same stance on the same topic, their assessment depends on the prior perception and weighting of the different aspects of the topic being discussed .…
MadDog A Web based System for Acronym Identification and Disambiguation
Acronyms and abbreviations are the short-form of longer phrases . They provide challenges for understanding the text especially if the acronym is not defined in the text or if it is used far from its definition in long texts . The web-based system is publicly available at http://iqcs.uoregon.edu:5000…
Performance Evaluation of Convolutional Neural Networks for Gait Recognition
In this paper, a performance evaluation of well-known deep learning models ingait recognition is presented . The transfer learning scheme is adopted to pre-trained models in order to fit the models to the CASIA-Bdataset for solving a gait recognition task .…
A new approach to extracting coronary arteries and detecting stenosis in invasive coronary angiograms
In stable coronary artery disease, reduction in mortality and/ormyocardial infarction with revascularization over medical therapy has not beenreliably achieved . We aim to develop an automatic algorithm by deep learning to extractcoronary arteries from ICAs . After segmentation, an arterial stenosis detection algorithm was developed to extract vascular centerlines and calculate arterial diameter to evaluate stenotic level .…
Estimating the Total Volume of Queries to a Search Engine
We study the problem of estimating the total number of searches (volume) ofqueries in a specific domain, which were submitted to a search engine in agiven time period . Our statistical model assumes that the distribution ofsearches follows a Zipf’s law, and that the observed sample volumes are biasedaccordingly to three possible scenarios .…
Blind Diagnosis for Millimeter wave Massive MIMO Systems
Millimeter-wave (mmWave) massive multiple-input multiple- input multiple-output (MIMO) systems rely on large-scale antenna arrays to combat large path-loss at mmWaveband . Current diagnostic techniques require full or partial knowledge of channel state information (CSI), which can be challenging to acquire in the presence of antenna failures .…
Domain Dependent Speaker Diarization for the Third DIHARD Challenge
This report presents the system developed by the ABSP Laboratory team for the third DIHARD speech diarization challenge . The performance substantially improved over that of thebaseline when we optimized the thresholds for agglomerative hierarchical clustering and the parameters for dimensionality reduction during scoring for individual acoustic domains .…
A two species micro macro model of wormlike micellar solutions and its maximum entropy closure approximations An energetic variational approach
Wormlike micelles are self-assemblies of polymer chains that can break and reform reversibly . The model incorporates a breaking and reforming process into the classical micro-macro dumbbell model forpolymeric fluids in a unified variational framework . By imposingproper dissipation in the coarse-grained level, the closure model, obtained by”closure-then-approximation”, preserves the thermodynamical structure of bothmechanical and chemical parts of the original system .…
Active Attack Detection and Control in Constrained Cyber Physical Systems Under Prevented Actuation Attack
This paper proposes an active attack detection scheme for constrained cyber-physical systems . The proposed scheme consists of two units: 1) detection, and 2) control . The detection unit includes a set of parallel detectors, which are designed based on themultiple-model adaptive estimation approach to detect the attack and to identify the attacked actuator(s).…
Personalization Paradox in Behavior Change Apps Lessons from a Social Comparison Based Personalized App for Physical Activity
Social comparison-based features are widely used in social computing apps . Most existing apps are not grounded in social comparison theories . This paper is among the first to automatically personalize socialcomparison targets . In the context of an m-health app for physical activity, we use artificial intelligence (AI) techniques of multi-armed bandits.…
Process Level Representation of Scientific Protocols with Interactive Annotation
Process Execution Graphs~(PEG) is a document-level representation of real-world wet lab biochemistry protocols . We manually annotate PEGs in a corpus of complex lab protocols with a novel interactive textual simulator . We use this data to developgraph-prediction models, finding them to be good at entity identification and local relation extraction, while our corpus facilitates further exploration of long-range relations .…
ECOL R Encouraging Copying in Novel Object Captioning with Reinforcement Learning
Novel Object Captioning is a zero-shot Image Captioning task requiringdescribing objects not seen in training captions . The ECOL-R model (Encouraging Copying ofObject Labels with Reinforced Learning) is encouraged to accurately describe the novel object labels . This isachieved via a specialised reward function in the SCST reinforcement learningframework (Rennie et al.,…
Unsupervised Anomaly Detection and Localisation with Multi scale Interpolated Gaussian Descriptors
Current unsupervised anomaly detection and localisation systems are commonlyformulated as one-class classifiers that depend on an effective estimation of the distribution of normal images and robust criteria to identify anomalies . However, the current systems tendsto be unstable for classes that are under-represented in the training set, and the anomaly identification criteria commonly explored in thefield does not work well for multi-scale structural and non-structuralanomalies .…
ATRM Attention based Task level Relation Module for GNN based Few shot Learning
graph neural networks (GNNs) have shown powerful ability to handle few-shot classification problem . GNNs aim to classify unseen samples whentrained with limited labeled samples per class . We propose a new relation measure method to explicitly model the task-level relation of one sample to all the others .…
On the Performance of Image Recovery in Massive MIMO Communications
Massive MIMO (Multiple Input Multiple Output) has demonstrated as a potential candidate for 5G-and-beyond wireless networks . Alow-pass filter is exploited to enhance efficiency of the remaining noiseand artifacts reduction in the recovered image. Numerical results demonstratethe necessity of a post-filtering process in enhancing the quality of imagerecovery.…
On the binary adder channel with complete feedback with an application to quantitative group testing
We determine the exact value of the optimal symmetric rate point in the Dueckzero-error capacity region of the binary adder channel with complete feedback . We establish that the minimum number of tests is asymptotic to $(\log_2 n) / r$ where the constant $r \approx 0.78974$ lies strictly betweenthe lower bound $5/7 / 2 is due to Gargano et al.…
Eigen convergence of Gaussian kernelized graph Laplacian by manifold heat interpolation
This work studies the spectral convergence of graph Laplacian to theLaplace-Beltrami operator when the graph affinity matrix is constructed from $N$ random samples on a $d$-dimensional manifold . By analyzing Dirichlet form convergence and constructingcandidate approximate eigenfunctions via convolution with manifold heat kernel, we prove that, with Gaussian kernel, one can set the kernel bandwidth parameter$\epsilon \sim (\log N/ N)^{1/(d/2+2)$ such that the eigenvalue convergencerate is $N^{-1/ d/2/d+3$ The result holds forun-normalized and random-walk graph LaPlacians when data are uniformly sampled on the manifold, as well as the density-corrected…
A Generalization of QR Factorization To Non Euclidean Norms
I propose a way to use non-Euclidean norms to formulate a QR-likefactorization . A classic QR factorization of a matrix$\mathbf{A}$ computes an upper triangular matrix and orthogonal matrix . I relax the orthogonalityrequirement for the norm to be Euclidean and instead require it have condition number $kappa (QQR) that is bounded independently of the matrix $A) .…
TSO DSO Operational Planning Coordination through Surrogate Lagrangian Relaxation
Difficulties behind creating TSO-DSO coordination include combinatorial nature of the operational planning problem involved at the transmission level as well asthe nonlinearity of AC power flow within both systems . Numerical results based on thecoordination of 118-bus TSO system with 32 DSO 34-bus systems indicate that both systems benefit from the coordination.…
Diverse Adversaries for Mitigating Bias in Training
Adversarial learning can learn fairer and less biased models of language than standard methods . However, current adversarial techniques only partiallymitigate model bias, added to which their training procedures are often unstable . In this paper, we propose a novel approach to adversarial learning based on the use of multiple diverse discriminators, whereby discriminators are encouraged to learn orthogonal hidden representations from one another .…
MICROS Mixed Initiative ConveRsatiOnal Systems Workshop
MICROS@ECIR2021 aims at investigating and collecting novel ideas and contributions in the field of conversational systems . The first edition of the workshop on Mixed-Initiative ConveatiOnal Systems will have a particular focus on mixed-initiative conversationalsystems . The workshop will focus on the way users access online information, thus posing new challenges compared to traditional search and recommendation .…
The Role of Cost in the Integration of Security Features in Integrated Circuits for Smart Cards
This essay investigates the role of cost in the development and production of secure integrated circuits . I also go on to examine potential ways of reducing the cost of production for secure chips . This essay ends with the conclusion that adding security features to chips meant to be used for secure applications is well worth it, because the potential damages and losses caused by such attacks are of comparable amounts to the costs of developing and producing a chip .…
Latent Factor Modeling of Users Subjective Perception for Stereoscopic 3D Video Recommendation
First-of-its-kind model that recommends 3D movies based on viewer’s subjective ratings accounting correlation between viewer’s visualdiscomfort and stereoscopic-artifact perception . The proposed model is trainedand tested on benchmark Nama3ds1-cospad1 and LFOVIAS3DPh2 S3D video qualityassessment datasets . The experiments revealed that resulting .…
Linking User Opinion Dynamics and Online Discussions
This paper studies the dynamics of opinion formation and polarization insocial media . We investigate whether the stance of users with respect to contentious subjects is influenced by online discussions that they are exposed to, and by the interactions with users supporting different stances .…
Zero rate reliability function for mismatched decoding
We derive an upper bound to the reliability function of mismatched decoding for zero-rate codes . The bound is based on a result by Koml\’os that shows theexistence of a subcode with certain symmetry properties . We conclude that the bound is shown to coincide with the expurgated exponent at rate zero for a broad family ofchannel and decoding metric pairs .…
Is Phase Shift Keying Optimal for Channels with Phase Quantized Output
This paper establishes the capacity of AWGN channels with phase-quantized output . We show that a rotated $2^b$-phase shift keying scheme is thecapacity-achieving input distribution for a complex AWGN channel . The outage performance is also investigatedfor the case of Rayleigh fading.…
CPT Efficient Deep Neural Network Training via Cyclic Precision
Low-precision deep neural network (DNN) training has gained tremendousattention as reducing precision is one of the most effective knobs for boosting DNNs’ training time/energy efficiency . We propose Cyclic Precision Training(CPT) to cyclically vary the precision between two boundary values which can be identified using a simple precision range test within the first few trainingepochs .…
Optimal Flexural Design of FRP Reinforced Concrete Beams Using a Particle Swarm Optimizer
The design of the cross-section of an FRP-reinforced concrete beam is aniterative process of estimating both its dimensions and the reinforcementratio . This paper intends to develop a preliminary least-costsection design model that follows the recommendations in the ACI 440.1 R-06 .…
A Data Driven Modeling Framework of Time Dependent Switched Dynamical Systems via Extreme Learning Machine
A data-driven modeling framework of switched dynamical systemsunder time-dependent switching is proposed . The learning technique is Extreme Learning Machine (ELM) The learning process includes segmented tracedata merging and subsystem dynamics modeling . The modeling process is formulated as an iterativeLeast-Squares (LS) optimization problem .…
Identity aware Graph Neural Networks
Message passing Graph Neural Networks (GNNs) provide a powerful modelingframework for relational data . The expressive power of existing GNNsis upper-bounded by the 1-Weisfeiler-Lehman (1-WL) graph isomorphism test . Here we develop a class of message passing GNNs, named Identity-awareGraph Neural Networks .…
Re imagining Algorithmic Fairness in India and Beyond
Conventional algorithmic fairness is West-centric, as seen in sub-groups,values, and methods . In India, data is notalways reliable due to socio-economic factors, ML makers appear to followdouble standards, and AI evokes unquestioning aspiration . We contend that localising model fairness alone can be window dressing in India, where the distance between models and oppressed communities is large .…
A Trigger Sense Memory Flow Framework for Joint Entity and Relation Extraction
Joint entity and relation extraction framework constructs a unified model to perform both tasks simultaneously . It can exploit the dependency between the two tasks to mitigate the error propagation problem suffered by the pipeline model . We build a memory module to remember categoryrepresentations learned in entity recognition .…
Cyber Physical Energy Systems Security Threat Modeling Risk Assessment Resources Metrics and Case Studies
Cyber-physical systems (CPS) are interconnected architectures that employanalog, digital, and communication resources for their interaction with thephysical environment . CPS are the backbone of enterprise, industrial, and critical infrastructure . Attackstargeting cyber-physical energy systems (CPES) can have disastrous consequences . The security of CPES can be enhancedleveraging testbed capabilities to replicate power systems operation, discovervulnerabilities, develop security countermeasures, and evaluate grid operation under fault-induced or maliciously constructed scenarios .…
Embedding based Instance Segmentation of Microscopy Images
EmbedSeg is an end-to-end trainable deep learning method based on the work by Neven et al. It uses the medoid instead of embedding each pixel to thecentroid of any given instance . The pipeline has a small enough memory footprint to be used on virtually all CUDA enabled laptop hardware .…
Creating a Virtuous Cycle in Performance Testing at MongoDB
Performance testing is part of the development process at MongoDB, and integrated into our continuous integration system . We believe that we have created and exploited a virtuous cycle:performance test improvements drive impact, which drives more use . Overall, MongoDB is gettingfaster and we avoid shipping major performance regressions to our customers because of this infrastructure .…
Age Debt A General Framework For Minimizing Age of Information
We consider the problem of minimizing age of information in generalsingle-hop and multihop wireless networks . We formulate a way to convert AoI optimization problems into equivalent network stability problems . Then, we propose a heuristic low complexity approach for achieving stability that can handle general network topologies; unicast, multicast and broadcast flows;interference constraints; link reliabilities; and AoI cost functions .…
UAV Assisted Over the Air Computation
Over-the-air computation (AirComp) provides a promising way to supportultrafast aggregation of distributed data . However, its performance cannot beguaranteed in long-distance transmission due to the distortion induced by the channel fading and noise . To unleash the full potential of AirComp, this paper proposes to use a low-cost unmanned aerial vehicle (UAV) acting as a mobilebase station to assist AirComp systems .…
Diffusion Asymptotics for Sequential Experiments
We propose a new diffusion-asymptotic analysis for sequentially randomized experiments . We let the mean signal level scale to the order$1/\sqrt{n}$ so as to preserve the difficulty of the learning task as $n$ gets large . In this regime, we show that the behavior of a class of methods forsequential experimentation converges to a diffusion limit .…
Particle Swarm Optimization Development of a General Purpose Optimizer
The particle swarmoptimization (PSO) method is sometimes viewed as another evolutionary algorithmbecause of their many similarities, despite not being inspired by the samemetaphor . The plain version can be programmed in a few lines of code, involving no operator design and few parameters to be tuned .…