Transfer Learning for Human & AI

Malware detection and analysis are active research subjects in cybersecurity over the last years . The usual detection methods do not necessarily provide tools to interpret the results . The proposed model can determine if a sample ispacked or encrypted with a precision of 85% .…

Compact convolutional neural networks (CNNs) have witnessed exceptionalimprovements in performance in recent years . However, they still fail toprovide the same predictive power as CNNs with a large number of parameters . Diverse features present in activation maps indicate presence of unique descriptors necessary to distinguish between objects of differentclasses .…

The Nested Relational Calculus (NRC) has been an influential high-level query language . It has been used as a basis for language-integrated queries in programming languages such as F#, Scala, and Links . However, NRC’s treatment of incomplete information, using nulls and three-valued logic, is not compatible with `standard’ NRC based on two-valued .…

This paper introduces the sixth Oriental Language Recognition (OLR) 2021Challenge . It intends to improve the performance of language recognitionsystems and speech recognition systems within multilingual scenarios . The dataprofile, four tasks, two baselines, and the evaluation principles are presented .…

Identification of so-called dynamic networks is one of the most challenging problems appeared recently in control literature . Bayesian approach introduces a new approach for linear dynamic networksidentification . It implements aggressive shrinkage of small impulse responses while larger impulse responses are conveniently subject to stable spline regularization .…

Deep learning (DL) techniques have achieved great success in predictive accuracy in a variety of tasks, but deep neural networks (DNNs) are shown toproduce highly overconfident scores for even abnormal samples . Well-defineduncertainty indicates whether a model’s output should (or should not) betrusted and thus becomes critical in real-world scenarios which typicallyinvolves shifted input distributions due to many factors .…

Neurofeedback games are an effective and playful approach to enhance certainsocial and attentional capabilities in children with autism . The games are promising to become widely accessible along with the commercialization of mobile EEG modules . However, little industry-based experiences are shared on how to better design neurofeedbacks games to fine-tune their playability and user experiences for autistic children .…

Single-photon cameras (SPCs) are an emergingsensing modality that are capable of capturing images with high sensitivity . Despite having minimal read-noise, images captured by SPCs in photon-starved conditions still suffer from strong shot noise . We propose photon scale-space a collection of high-SNR imagesspanning a wide range of photons-per-pixel (PPP) levels as guides to train inference model on low photon flux images .…

Conditional computation and modular networks have been recently proposed formultitask learning and other problems as a way to decompose problem solving into multiple reusable computational blocks . We propose a new approach forlearning modular networks based on the isometric version of ResNet with allresidual blocks having the same configuration and the same number of parameters .…

Understanding emotions that people express during large-scale crises helps inform policy makers and first responders about theemotional states of the population . We present CovidEmo, ~1K tweets labeled withemotions. We examine how well large pre-trained language models generalizeacross domains and crises in the task of perceived emotion prediction .…

Sepsis is a life-threatening disease with high morbidity, mortality and health care costs . Early prediction and administration of antibiotics and fluids is considered crucial for the treatment of sepsis and can save potentially millions of lives and billions in health care .…

Skyline plays a pivotal role in mountainous visual geo-localization and localization/navigation of planetary rovers/UAVs and virtual/augmented realityapplications . We present a novel mountainous skyline detection approach wherewe adapt a shallow learning approach to learn a set of filters to discriminate between edges belonging to sky-mountain boundary and others coming from different regions .…

The method significantly compressesneural network weights to a sparse ternary of [-1,0,1 . It can compress aResNet-18 model from 46 MB to 955KB and a ResNet-50 model from 99 MB to 3.3MB (~30x) The top-1 accuracy on ImageNet drops slightly from 69.7% to65.3% and from 76.15% to 74.47% .…

The Shapley value is one of the most widely used model-agnostic measures offeature importance in explainable AI . It has clear axiomatic foundations, is guaranteed to uniquely exist, and has a clear interpretation as a feature’saverage effect on a model’s prediction .…

By lumping all dangling nodes of a web graph into a single node, PageRankcomputation can be proceeded with a much smaller matrix on the case that thenumber of dangling nodes is large . Thus, it saves many computational cost and operations .…

Octo-Tiger is a code for modeling three-dimensional self-gravitatingastrophysical fluids . It was particularly designed for the study of dynamicalmass transfer between interacting binary stars . We present scaling results for the newhydro kernels on ORNL’s Summit machine using a Sedov-Taylor blast wave problem .…

A paper uses distanceregularized level set (DRL SE) to explore the segmentation effect of epicardiumand endocardium . Five CT images are used to verify the proposedmethod, and image quality evaluation indexes such as dice score and Hausdorffdistance are used . The results showed that the researchers could separate the inner and outer membrane very well (endocardiumdice = 0.9253, Hausorfff = 7.8740) and epicocardium Hausdice= 0.9687 .…

Unrealistic feature suppression (UFS) module keeps high-quality features and suppresses unrealistic features . UFS module keeps the training stability of networks and improves the quality ofgenerated images . We demonstrate effectiveness of the module on various models such as WGAN-GP, SNGAN, and BigGAN .…

The paper proposes a novel approach for gray scale images segmentation . It is based on multiple features extraction from single feature per image pixel, using Echo state network . The newly extractedfeatures — reservoir equilibrium states — reveal hidden image characteristicsthat improve its segmentation via a clustering algorithm .…

Symmetries are widespread in physical, technological, biological, and social networks, including power grids . The swing equation is a classic model for the dynamics of powergrid networks . The main goal of this paper is to explain how network symmetries affect the swing equation transient and steadystate dynamics .…

In this paper, we connect the tools from cryptology and complexity theory in the domain of Boolean functions with low polynomial degree and high sensitivity . We show that one can implement resilientBoolean functions on a large number of variables with linear size andlogarithmic depth .…

Value iteration is a well-known method of solving Markov Decision Processes . However, the computational cost of value iteration quickly becomesfeasible as the size of the state space increases . In this paper, we propose an intuitive algorithm for solving MDPsthat reduces the cost of updates by dynamically grouping together states with similar cost-to-go values .…

Autonomous Micro Aerial Vehicles (MAVs) have the potential to be employed for surveillance and monitoring tasks . By perching and staring on one or multiplelocations aerial robots can save energy while concurrently increasing theiroverall mission time without actively flying . The onboard cameras and IMU are concurrently used for state estimation and to inferthe relative robot/target localization .…

The AAGC-LSTM combines spatial and temporal dependency in a single network operation . This is made possible by equipping graph convolutions with adjacency adaptivity, which allows for learning unknown dependencies of the human body joints . Tofurther boost accuracy, we propose longitudinal loss weighting to considernatural movement patterns, as well as body-aware contralateral dataaugmentation .…

Graph neural networks (GNNs) have achieved remarkable success as a framework for deep learning on graph-structured data . However, GNNs are fundamentallylimited by their tree-structuring inductive bias . We propose to augment the GNN message-passing operations with information on ego graphs (i.e.,…

Practical Byzantine Fault Tolerance (PBFT) is a seminal state machinereplication protocol that achieves a performance comparable to non-replicated systems in realistic environments . One of these optimizations is read-only requests, a particular type of client request which avoids running the three-step agreement protocol and allows replicas to respond directly, thus reducing the latency of reads from five to two communication steps .…

Most of existing studies on adaptive submodular optimization focus on theaverage-case, i.e., their objective is to find a policy that maximizes theexpected utility over a known distribution of realizations . We introduce a new class ofstochastic functions, called \emph{worst-case submodular function .…

SuperCaustics is a real-time,open-source simulation of transparent objects designed for deep learning applications . It uses hardware ray-tracing to support caustics, dispersion, and refraction . The neural network achieved performance comparable to the state-of-the-art on a real world dataset using only 10% of the training data and in a fraction of training time .…

The combined use of multiple modalities enables accurate pedestrian detection under poor lighting conditions by using the high visibility areas from thesemodalities together . The vital assumption for the combination use is that thereis no or only a weak misalignment between the two modalities .…

Many quantum (convolutional) circuit ansaetze are proposed forgrayscale images classification tasks with promising empirical results . But the intra-channel information that is useful for vision tasks is not extracted effectively . This is the first work of a quantum convolutional circuit to deal with RGB images with a higher test accuracy compared to the purely classical CNNs .…

We introduce a runtime-efficient tree hashing algorithm for the identification of isomorphic subtrees . We propose a simple diversity-preservationmechanism with promising results on a collection of symbolic regressionbenchmark problems . The algorithm has two important applications: fast calculation ofpopulation diversity and algebraic simplification of symbolic expression trees .…

We describe a project to formalize Galois theory using the Lean theoremprover . We discuss some of the challenges we faced and the decisions we made in the course of this project . The maintheorems we formalized are the primitive element theorem, the fundamentaltheorem of Galois Theory, and the equivalence of several characterizations offinite degree Galois extensions .…

Deep learning models have gained great popularity in statistical modeling . Theadvantage of deep learning models is that their solutions are difficult tointerpret and explain . We propose a new network architecture that sharessimilar features as generalized linear models, but provides superior predictivepower benefiting from the art of representation learning .…

Many quantum (convolutional) circuit ansaetze are proposed forgrayscale images classification tasks with promising empirical results . But the intra-channel information that is useful for vision tasks is not extracted effectively . This is the first work of a quantum convolutional circuit to deal with RGB images with a higher test accuracy compared to the purely classical CNNs .…

Session types enable the static verification of message-passing programs . Asession type specifies a channel’s protocol as sequences of messages . This paper establishes a minimality result but now for the session\pi-calculus, the language in which values are names and for which sessiontypes have been more widely studied .…

CARP (Collision Avoidance byReciprocal Projections) is effective even when the estimates of otheragents’ positions and velocities are noisy . The method’s main computational step involves the solution of a small convex optimization problem, which can be easily solved in practice, even on embedded platforms .…

The goal of Unsupervised Anomaly Detection (UAD) is to detect anomalous signals under the condition that only non-anomalous (normal) data is available before . In UAD-S, data is exposed to contextual changes that are usually unknown beforehand . In our exploratory investigation, we look for two qualities, Separability (SEP) and Discriminative Support (DSUP) and formulate several hypotheses that could facilitate diagnosis and development of further representation and detection approaches .…

Visual DomainAdaptation (VisDA) 2021 competition tests models’ ability to adapt to novel test distributions and handle distributional shift . Ourchallenge draws on large-scale publicly available datasets but constructs the evaluation across domains . Performance will be measured using a rigorous protocol,comparing to state-of-the-art domain adaptation methods with the help ofestablished metrics .…

Deep learning-based 3D object detection has achieved unprecedented success with the advent of large-scale autonomous driving datasets . However, drasticperformance degradation remains a critical challenge for cross-domain deployment . We propose anovel and unified framework, Multi-Level Consistency Network (MLC-Net), whichemploys a teacher-student paradigm to generate adaptive and reliablepseudo-targets .…

We propose a novel method for solving regression tasks using few-shot or weaksupervision . At the core of our method is the fundamental observation that GANsare incredibly successful at encoding semantic information within their latentspace, even in a completely unsupervised setting .…

Federated Learning (FL) is known to perform Machine Learning tasks in adistributed manner . A challenge that exists in FL is the communication costs, as FLtakes place in a distributed environment where devices connected over thenetwork have to constantly share their updates this can create a communication bottleneck .…

Hard parameter sharing in multi-task learning (MTL) allows tasks to sharesome of model parameters, reducing storage cost and improving prediction accuracy . The common sharing practice is to share bottom layers of a deepneural network among tasks while using separate top layers for each task .…

Language instruction plays an essential role in the natural language groundednavigation tasks . We propose a DynamicReinforced Instruction Attacker (DR-Attacker) which learns to mislead thenavigator to move to the wrong target by destroying the most instructive information in instructions at different timesteps .…

Fastmultipole methods (FMM) are used to accelerate the matrix vector products needed . The method is based on recursions of themultipole moments for $O(1) cost per moment with a low asymptotic constant . The derived recursions are tested both for accuracy and performance .…

Archaeological data have many different formats (images,texts, sensor data) and can be structured, semi-structured and unstructured . Such variety makes data difficult to collect, store, manage, search and analyze . We propose a generic, flexible andcomplete data lake architecture . Our metadata management system exploitsgoldMEDAL, which is the most complete metadata model currently available .…

Aligned Disentangling Generative AdversarialNetwork (AD-GAN) introduces representationdisentanglement to separate content representation from style representation . With this framework, spatial structure can be preserved explicitly, enabling asignificant reduction of macro-level lossy transformation . AD-GAN leads to significant improvement over the current best unsupervised methods by an average 17.8% relatively (w.r.t.…

In this paper, we propose a numerical scheme for fluid models of magnetisedplasmas . One important feature of the numerical scheme is that it should beable to handle the anisotropy induced by the magnetic field . We propose the use of the hybrid mimetic mixed (HMM) scheme for diffusion .…

We investigate a new threat to neural sequence-to-sequence (seq2seq) models: training-time attacks that cause models to “spin” their output and support acertain sentiment . We introduce the concept of a “meta-backdoor” to explain model-spinningattacks . These attacks produce models whose output is valid and preservescontext, yet also satisfies a meta-task chosen by the adversary (e.g.,…

Scheduled sampling is an effective method to alleviate the exposure biasproblem of neural machine translation . It simulates the inference scene by replacing ground-truth target input tokens with predicted ones during training . Despite its success, its critical schedule strategies are merelybased on training steps, ignoring the real-time model competence .…

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.…