Simple Light Yet Formally Verified Global Common Subexpression Elimination and Loop Invariant Code Motion

We present an approach for implementing a formally certified loop-invariantcode motion optimization by composing an unrolling pass and an efficient global subexpression elimination . Each pass comes with a simple and independent proof ofcorrectness . The approach significantly narrows the performance gap between the CompCert certified compiler and state-of-the-art optimizingcompilers .…

Automatic Learning to Detect Concept Drift

Active Drift Detection with Meta learning (Meta-ADD) is a novel framework that learns to classify concept drift by tracking the changed pattern of error rates . Meta-ADD uses machine learning to learn to detect concept drifts and identify their types automatically, which candirectly support drift understand .…

An Overview of Laser Injection against Embedded Neural Network Models

The deployment of models in a large variety of devices faces several obstacles related to trust and security . Fault Injection Analysis (FIA) are known to be very powerful with a large spectrum of attack vectors . Laser injection with state-of-the-art equipment, combined with theoretical evidences from Adversarial Machine Learning, highlights worryingthreats against the integrity of deep learning inference and claims that joinefforts from the theoretical AI and Physical Security communities are a urgent need .…

An Empirical Review of Deep Learning Frameworks for Change Detection Model Design Experimental Frameworks Challenges and Research Needs

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 .…

Dual Cross Central Difference Network for Face Anti Spoofing

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 .…

Technical Report for Valence Arousal Estimation on Affwild2 Dataset

In this work, we describe our method for tackling the valence-arousalestimation challenge from ABAW FG-2020 Competition . The competition organizers provide an in-the-wild Aff-Wild2 dataset for participants to analyze affectivebehavior in real-life settings . We use MIMAMO Net to achieve information about micro-motion and macro-motion for improving videoemotion recognition .…

Collaborative Multi Resource Allocation in Terrestrial Satellite Network Towards 6G

Terrestrial-satellite networks are envisioned to play a significant role inthe sixth-generation (6G) wireless networks . In such networks, hot air balloons are useful as they can relay the signals between satellites and groundstations . Most existing works assume the same height with the same minimum elevation angle to the satellites, which may not be practical due to possible route conflict with airplanes and otherflight equipment .…

Canonical Saliency Maps Decoding Deep Face Models

The Canonical Saliency Maps highlight facial features responsible for the decision made by a deep face model on a given image . Image-level maps highlight facialfeatures responsible for a DNN decision, thus helping to understand how a . DNN made a prediction on the image .…

Weak Multi View Supervision for Surface Mapping Estimation

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 .…

Hallucination Improves Few Shot Object Detection

Learning to detect novel objects from few annotated examples is of greatpractical importance . A particularly challenging yet common regime occurs whenthere are extremely limited examples (less than three) One critical factor in improving few-shot detection is to address the lack of variation in training data .…

Self Supervised Approach for Facial Movement Based Optical Flow

Deep learning-based optical flow techniques do not perform well for non-rigidmovements such as those found in faces . We hypothesize that learning opticalflow on face motion data will improve the quality of predicted flow on faces . The performance of FlowNetS trained on face images surpassed that of other opticalflow CNN architectures, demonstrating its usefulness.…

Data Efficient Reinforcement Learning for Malaria Control

The main challenge faced by policymakers is to learn a policy from scratch by interacting with a complex environment in a few trials . This work introduces apractical, data-efficient policy learning method, named Variance-Bonus MonteCarlo Tree Search~(VB-MCTS) It can copy with very little data andfacilitate learning from scratch in only a few trial times .…

Effects of Quantization on the Multiple Round Secret Key Capacity

We consider the strong secret key (SK) agreement problem for the satellitecommunication setting . Legitimate receivers have access to an authenticated, noiseless, two-way, and public communication link . The noise variances for Alice’s and Bob’s measurement channels are both fixed to a value $Q1$, whereas the noise over Eve’s measurement channel has a unitvariance, so $Q$ represents a channel quality ratio .…

Autonomous Robotic Mapping of Fragile Geologic Features

Robotic mapping is useful in scientific applications that involve surveyingunstructured environments . This paper presents a target-oriented mapping system for sparsely distributed geologic surface features, such as precariouslybalanced rocks (PBRs), whose geometric fragility parameters can provide valuable information on earthquake shaking history and landscape development .…

Walk in the Cloud Learning Curves for Point Clouds Shape Analysis

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 .…

Eigenfactor

The Eigenfactor is a journal metric, which was developed by Bergstrom and his colleagues at the University of Washington . It establishes the importance, influence or impact of a journal based on its location in a network of journals . While journal-basedmetrics have been criticized, it has also been suggested as analternative in the widely used San Francisco Declaration on Research Assessment(DORA) The algorithm is based on Eigenvector centrality, i.e.…

QSOC Quantum Service Oriented Computing

Quantum computing is quickly turning from a promise to a reality, witnessing the launch of several cloud-based, general-purpose offerings, and IDEs . Quantum Service-Oriented Computing (QSOC) is a model-driven methodology to allow DevOps teams to compose, configure and operate enterprise applications without intimate knowledge on the underlying quantuminfrastructure .…

MLP Mixer An all MLP Architecture for Vision

Convolutional Neural Networks (CNNs) are the go-to model for computer vision . Attention-based networks, such as the Vision Transformer, have also become popular . In this paper we show that while convolutions and attention are sufficient for good performance, neither of them are necessary .…

HASCO Towards Agile HArdware and Software CO design for Tensor Computation

Tensor computations overwhelm traditional general-purpose computing devices . They callfor a holistic solution composed of both hardware acceleration and softwaremapping . Hardware/software (HW/SW) co-design optimizes the hardware andsoftware in concert and produces high-quality solutions . Hasco achieves a 1.25X to 1.44Xlatency reduction through HW/SW co-Design compared with developing the hardwareand software separately .…

Deep Reinforcement Learning for Adaptive Exploration of Unknown Environments

The proposed approach uses a map segmentation technique to decompose the environment map into smaller, tractable maps . A simple information gain function is computed to determine the best target region to search during eachiteration of the process . DDQN and A2C algorithms are extended with a stack ofLSTM layers and trained to generate optimal policies for the exploration andexploitation, respectively .…

Towards Accountability in the Use of Artificial Intelligence for Public Administrations

We argue that distributed responsibility, inducedacceptance, and acceptance through ignorance constitute instances of imperfectdelegation when tasks are delegated to computationally-driven systems . We hold that both directpublic accountability via public transparency and indirect publicaccountability via transparency to auditors in public organizations can be bothinstrumentally ethically valuable and required as a matter of deontology from the principle of democratic self-government .…

Two Stage Facility Location Games with Strategic Clients and Facilities

We consider non-cooperative facility location games where both facilities and clients act strategically and heavily influence each other . This contrasts established game-theoretic facility location models with non-strategic clientsthat simply select the closest opened facility . We focus on a natural client behavior similar to classical loadbalancing: our selfish clients aim for a distribution that minimizes their maximum waiting times for getting serviced, where a facility’s waiting timecorresponds to its total attracted client weight .…

Deterministic Rounding of Dynamic Fractional Matchings

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 .…

Implicit differentiation for fast hyperparameter selection in non smooth convex learning

Finding the optimal hyperparameters of a model can be cast as a bileveloptimization problem, typically solved using zero-order techniques . In thiswork we study first-order methods when the inner optimization problem is convexbut non-smooth . We show that the forward-mode differentiation of proximal gradient descent and proximal coordinate descent yield sequences of Jacobiansconverging toward the exact Jacobian .…

Simulation by Rounds of Letter to Letter Transducers

Letter-to-letter transducers are a standard formalism for modeling reactivesystems . Often, two transducers that model similar systems differ locally fromone another, by behaving similarly, up to permutations of the input and outputletters within “rounds” In our setting,words are partitioned to consecutive subwords of a fixed length $k$ calledrounds .…

Learning 3D Granular Flow Simulations

Graph Neural Networks approach towards accurate modeling of complex 3D granular flow simulation processes . We discuss how to implement GraphNeural Networks that deal with 3D objects, boundary conditions, particle -particle, and particle – boundary interactions . We compare themachine learning based trajectories to LIGGGHTS trajectories in terms of particle flows and mixing entropies.…

Where and When Space Time Attention for Audio Visual Explanations

Recent advances in XAI provide explanations for models trained on still images . But when it comes to modeling multiplesensory modalities in a dynamic world, it remains underexplored how tomystify the mysterious dynamics of a complex multi-modal model . We propose a novel space-time attention network that uncovers the synergistic dynamics of audio and visual data overboth space and time .…

Environment Modeling During Model Checking of Cyber Physical Systems

Modelchecking has been proposed for validation of Cyber-Physical Systems . Adomain-independent framework based on timed-automata is proposed forabstraction and refinement of environment models during model checking . The framework maintains an abstraction tree of environment model models, which provides counter-examples interpretable by experts in the application domain .…

Optimal Algorithms for Range Searching over Multi Armed Bandits

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 .…