Transfer Learning for Human & AI

Model pruning is an effective technique to reduce computation overhead for deep neural networks . Modern recommendation systems are thirsty for model capacity due to the demand for handling big data . Pruning a recommendation model at scale results in a smaller model capacity and lower accuracy .…

Decentralized nonconvex optimization has received increasing attention in machine learning due to its advantages in system robustness, data privacy, and implementation simplicity . We show that to reach an$\epsilon^2$-stationary solution, the total number of sample evaluations of our algorithm is $1/2 .…

Insummary, by expanding the language of propositional logic, we make its prooftheory more regular and generate more proofs, some of which are very efficient . We design a proof system for propositional classical logic that integratestwo languages for Boolean functions .…

The digital transformation has been underway, creating digital shadows of(almost) all physical entities and moving them to the Internet . The era ofInternet of Everything has therefore started to come into play, giving rise tounprecedented traffic growths . Optical core networks forming the backbone of Internet infrastructure have been under critical issues ofreaching the capacity limit of conventional fiber, a phenomenon widely referredas capacity crunch .…

This work explores the use of computer vision for image segmentation and classification of medical fluid samples in transparent containers . Handling fluids such as infusion fluids,blood, and urine samples is a significant part of the work carried out in medical labs and hospitals .…

Hand Gesture Recognition (HGR) based on inertial data has grown considerably in recent years . The state-of-the-art approaches utilize a single sensor and a vocabulary comprised of simple gestures . In this work we explore the benefits of using multiple inertial sensors .…

System tightly couples multi-sensorperception and localisation to continuously learn from self-supervised pseudolabels . System improves by 60% in segmentation and 10% in localisation compared to deployment of a fixed model, and it keepsthis improvement up while adapting to further environments .…

Static analysis hasthe potential to provide early feedback on performance problems to developers without having to run profilers with expensive (and often unavailable) tests . We develop a tool that integrates the staticperformance analysis results from Infer via code annotations and decorations .…

Probabilistic matrix factorization (PMF) is a well-known model of recommendersystems . With the development of image recognition technology, some PMFrecommender systems that combine images have emerged . This study proposes anovel probabilistic model that integrates double convolutional neural networks into PMF .…

The use of video surveillance in public spaces has attracted considerable attention in recent years . But it has been difficult to systematically measure the prevalence and placement of cameras . Here we present a novel approach forestimating the spatial distribution of surveillance cameras .…

There are numerous e-assessment systems devoted to specific domains underdiverse license models . Cost, extensibility, and maintainability are relevant issues for an institution . Ease of use and inclusion into courses are main concerns . For students the user experience and fast transparent feedback plus “better” tests are most important .…

Citadel is a scalable collaborative ML system that protects the privacy of both data owner and model owner in untrusted infrastructures . Citadel performs distributed training across multiple training enclaves running on behalf of data owners and an aggregatorenclave . Citadel scales to alarge number of enclaves with less than 1.73X slowdown caused by SGX .…

We present a framework for deterministically rounding a dynamic fractional matching algorithm . This is the first dynamic matching algorithm that works on general graphs by using an algorithm for low-arboricity graphs as ablack-box subroutine . Our rounding scheme works by maintaining a good {\em matching-sparsifier} with bounded arboricity, and then applying the algorithm of Peleg and Solomon[SODA’16] to maintain a near-optimal matching in this low arboric graph .…

This study analyzed the performance of different machine learning methods for winter wheat yield prediction using extensive datasets of weather, soil, and phenology . The results indicated that nonlinear models such as deep neuralnetworks (DNN) and XGboost are more effective in finding the functionalrelationship between the crop yield and input data compared to linear models .…

Wind farm needs prediction models for predictive maintenance. There is a need to predict values of non-observable parameters beyond ranges reflected in available data . Physics-based principles are combined with machinelearning algorithms through feature engineering, strong rules anddivide-and-conquer. The proposed synergy concept is illustrated with the windturbine blade icing prediction and achieves significant prediction accuracyacross different turbines .…

The Isolation Lemma is a self-reduction scheme that allows one to assume that a given instance of a problem has a unique solution . In this paper, we study a setting that is more typical for $\mathsf{NP}$-complete problems, and obtain partial derandomizations in theform of significantly decreasing the number of required random bits .…

ACM and IEEEComputer Society’s Computer Science curricular guidelines have recommendedexposure to PDC concepts since 2013 . PDC curricular content, lectures, and labs freely available for undergraduate computer science programs . Despite efforts, progress inensuring computer science students graduate with sufficient PDC exposure has been uneven .…

We present a number of complexity results concerning the problem of counting vertices of an integral polytope . The focus is on polytopes with small integer vertices, particularly 0/1polytopes .…

Hadamard matrices are square $n\times n$ matrices whose entries are ones and minus ones . Matrices are orthogonal to each other with respect to the standard scalar product in $\Bbb R^n$. Each Hadamar matrix can be transformed to a matrix whose entries were zeros and ones .…

An intersection digraph is a digraph where every verticle $v$ is represented by an ordered pair $S_v, T_v$ of sets such that there is an edge from $v $w$ to $W$ if $V$ and $T_w$ intersect . We introduce a novel framework of directed versions of locally checkable problems, that streamlinesthe definitions and the study of many problems in the literature andfacilitates their common algorithmic treatment .…

Face anti-spoofing (FAS) plays a vital role in securing face recognitionsystems . Central difference convolution (CDC) has shown its excellent capacity for the FAS task via leveraging local gradientfeatures . However, aggregating central difference clues from allneighbors/directions simultaneously makes CDC redundant and sub-optimized .…

Recent advances in deep clustering and unsupervisedrepresentation learning are based on the idea that different views of an inputimage must be closer in therepresentation space . Consensus Clustering usingUnsupervised Representation Learning (ConCURL) improves the clusteringperformance over state-of-the art methods on four out of five image datasets .…

Graph convolution networks have recently garnered a lot of attention forrepresentation learning on non-Euclidean feature spaces . In this work, we propose a novel Multipath Graphconvolutional neural network that aggregates the output of multiple different shallow networks . Results show that the proposed method attains increased test accuracy but also requires fewer trainingepochs to converge .…

A unified system integrating a compact object detector and a surroundingenvironmental condition classifier for enhancing the robustness of objectdetection scheme in advanced driver assistance systems (ADAS) is proposed in this paper . The proposed system includes two main components: (1) a compactone-stage object detector which is expected to be able to perform at acomparable accuracy compared to state-of-the-art object detectors, and (2) an environmental condition detector that helps to send a warning signal to the cloud in case the self-driving car needs human actions due to the significance of the situation .…

We propose a weakly-supervised multi-view learning approach to learn category-specific surface mapping without dense annotations . We learn theunderlying surface geometry of common categories, such as human faces, cars,and airplanes, given instances from those categories . Our approach leverages information from multiple views of the object to establish additional consistency cycles, thus improving surface mapping understanding .…

As robots interact with a broader range of end-users, end-user robotprogramming has helped democratize robot programming . This article surveys work on work on robot programming, with a focus on program specification . The survey concludes by highlighting open directions for further investigation to enhance and widen the reach of robot programming systems .…

Discrete point cloud objects lack sufficient shape descriptors of 3Dgeometries . In this paper, we present a novel method for aggregatinghypothetical curves in point clouds . Sequences of connected points (curves) areinitially grouped by taking guided walks in the point clouds, and then aggregated back to augment their point-wise features .…

TimeGym Forecasting Debugging Toolkit is a Python library fortesting and debugging time series forecasting pipelines . It provides generic tests for forecasting pipelines fresh out of the box . The library enables forecasters to apply aTest-Driven Development approach to forecast modeling, using specified oraclesto generate artificial data with noise .…

We present a deep learning method to learn the macroscopic traffic speed dynamics from these space-time visualizations . We present the high-resolution traffic speed fields estimated for several freeway sections . We further demonstrate the quality and utility of the estimation by inferring vehicle trajectories from the estimated speedfields .…

In this work, we introduce a convex optimization strategy to train quantized NNs with polynomial activations . Our method leverages hiddenconvexity in two-layer neural networks from the recent literature, semidefinitelifting, and Grothendieck’s identity . We show that certainquantized NN problems can be solved to global optimality in polynnomine-time in Polynomial-time .…

This paper studies a multi-armed bandit (MAB) version of the range-searching problem . In its basic form, range searching considers as input a set of points and a collection of (real) intervals . The current work addresses range searching with stochastic weights: eachpoint corresponds to an arm (that admits sample access) and the point’s weightis the (unknown) mean of the underlying distribution .…

Visual change detection is one of the elementary tasks in computervision and video analytics . Applications include anomaly detection, object tracking, traffic monitoring, human machine interaction, behavior analysis, action recognition, and visual surveillance . The challenges in change detection include background fluctuations,illumination variation, weather changes, intermittent object motion, shadow, camera motion, and heterogeneous object shapes .…

Re-ranking utilizes contextual information to optimize the initial rankinglist of person or vehicle re-identification (re-ID) This paper proposes a re-ranking networkto predict the correlations between the . probe and top-ranked neighbor samples . The process is equivalent to moving independent embeddings toward theidentity centers, improving cluster compactness .…

Model quantization has been successfully applied in many practical applications . When the precision of quantization is adjusted, it is necessary to fine-tune the model or minimize the quantization noise . We propose a method to train a model for all quantization that supports diverse bit-widths .…

There are numerous e-assessment systems devoted to specific domains underdiverse license models . Cost, extensibility, and maintainability are relevant issues for an institution . Ease of use and inclusion into courses are main concerns . For students the user experience and fast transparent feedback plus “better” tests are most important .…

A deep-learning-based surrogate model capable of predicting flow andgeomechanical responses in CO2 storage operations is presented and applied . The surrogate model is trained topredicting the 3D CO2 saturation and pressure fields in the storage aquifer, and 2D displacement maps at the Earth’s surface .…

The main goal of NeuralLog is to bridge logic programming and deep learning . The main advantages of neural networks are: to allow neural networks to be defined as logic programs; and to be able to handlenumeric attributes and functions .…

Multiple-instance learning is a subset of weakly supervised learning where labels are applied to sets of instances rather than the instances themselves . This paper introduces a series of multiple-instances learning benchmarks . The benchmarks are available from PyPi as mil-benchmarksand on GitHub .…

Machine learning contrasts with traditional software development in that theoracle is the data, and the data is not always a correct representation of the problem that machine learning tries to model . We present a survey of the oracle issues found in machine learning and state-of-the-art solutions for dealing with these issues .…

As 5th Generation research reaches the twilight, the research community must look beyond 5G and look towards the 2030 connectivity landscape, namely 6G . Virtual mobile small cells (MSC) are created on demand and can harness radio and networking capability locally reducing protocol signaling latency and overhead .…

The advent of the big data era drives the media data owner to seek help from the cloud platform for data hosting and sharing . Sharing media data through thecloud suffers three key security/privacy problems including the leakage of dataprivacy, the infringement on the data owner’s copyright, and the infringementon the user’s right .…

Citrus segmentation is a key step of automatic citrus picking . Most current image segmentation approaches achieve good segmentation results bypixel-wise segmentation . These methods require alarge amount of annotated data, and do not consider continuous temporalchanges of citrus position in real-world applications .…

There are numerous e-assessment systems devoted to specific domains underdiverse license models . Cost, extensibility, and maintainability are relevant issues for an institution . Ease of use and inclusion into courses are main concerns . For students the user experience and fast transparent feedback plus “better” tests are most important .…

The U.S. Department of Energy’s ARPA-E issued a research project called SCOTTIE – Systematic CommunicationObjectives and Telecommunications Technology Investigations and Evaluations . SCOTTie tests virtual and augmented reality platforms in a functionalcomparison with face-to-face (FtF) interactions to derive travel replacementthresholds for common industrial training scenarios .…

C. elegans shows chemotaxis using klinokinesis where the worm senses the concentration based on a single concentration sensor to compute the concentration gradient to perform foraging through gradient ascent/descenttowards the target concentration . The biomimeticimplementation requires complex neurons with multiple ion channel dynamics aswell as interneurons for control .…

Recent skeleton-based actionrecognition methods extract features from 3D joint coordinates asspatial-temporal cues . We propose fusing third-orderfeatures in the form of angles into modern architectures, to robustly capture relationships between joints and body parts . This simple fusion with spatial-temporality graph neural networks achieves new state-of-the-artaccuracy in two large benchmarks, including NTU60 and NTU120, while employing fewer parameters and reduced run time .…

Many users, especially older adults, are not aware of accessibility features or do not know which combination to use . Automated recommendation could help people find beneficial accessibility features, authors say . Their work demonstrates the need to increase awareness of existing accessibility features on mobile devices .…

Industrial Internet-of-Things (IIoT) facilitates efficiency and robustness in factory operations . The synergy of complex event processing (CEP) and machinelearning (ML) has been developed actively in the last years in IIoT to identify patterns in heterogeneous data streams and fuse raw data into tangible facts .…

Most video super-resolution methods focus on restoring high-resolution videoframes from low-resolution videos without taking into account compression . Most videos on the web or mobile devices are compressed, and the compression can be severe when the bandwidth is limited . In this paper, we propose a new compression-informed video-super-resolution model to restorehigh-resolution content without introducing artifacts caused by compression .…