Statistical Modeling Of Hpc Performance Variability And Communication,
2021
University of New Mexico
Statistical Modeling Of Hpc Performance Variability And Communication, Jered B. Dominguez-Trujillo
Computer Science ETDs
Understanding the performance of parallel and distributed programs remains a focal point in determining how compute systems can be optimized to achieve exascale performance. Lightweight, statistical models allow developers to both characterize and predict performance trade-offs, especially as HPC systems become more heterogeneous with many-core CPUs and GPUs. This thesis presents a lightweight, statistical modeling approach of performance variation which leverages extreme value theory by focusing on the maximum length of distributed workload intervals. This approach was implemented in MPI and evaluated on several HPC systems and workloads. I then present a performance model of partitioned communication which also uses …
Smart Parking Systems: Reviewing The Literature, Architecture And Ways Forward,
2021
Old Dominion University
Smart Parking Systems: Reviewing The Literature, Architecture And Ways Forward, Can Biyik, Zaheer Allam, Gabriele Pieri, Davide Moroni, Muftah O' Fraifer, Eoin O' Connell, Stephan Olariu, Muhammad Khalid
Computer Science Faculty Publications
The Internet of Things (IoT) has come of age, and complex solutions can now be implemented seamlessly within urban governance and management frameworks and processes. For cities, growing rates of car ownership are rendering parking availability a challenge and lowering the quality of life through increased carbon emissions. The development of smart parking solutions is thus necessary to reduce the time spent looking for parking and to reduce greenhouse gas emissions. The principal role of this research paper is to analyze smart parking solutions from a technical perspective, underlining the systems and sensors that are available, as documented in the …
Efficient Algorithms For Identifying Loop Formation And Computing Θ Value For Solving Minimum Cost Flow Network Problems,
2021
Old Dominion University
Efficient Algorithms For Identifying Loop Formation And Computing Θ Value For Solving Minimum Cost Flow Network Problems, Timothy Michael Chávez, Duc Thai Nguyen
Computational Modeling & Simulation Engineering Faculty Publications
While the minimum cost flow (MCF) problems have been well documented in many publications, due to its broad applications, little or no effort have been devoted to explaining the algorithms for identifying loop formation and computing the value needed to solve MCF network problems. This paper proposes efficient algorithms, and MATLAB computer implementation, for solving MCF problems. Several academic and real-life network problems have been solved to validate the proposed algorithms; the numerical results obtained by the developed MCF code have been compared and matched with the built-in MATLAB function Linprog() (Simplex algorithm) for further validation.
Unsupervised Representation Learning By Predicting Random Distances,
2021
Singapore Management University
Unsupervised Representation Learning By Predicting Random Distances, Hu Wang, Guansong Pang, Chunhua Shen, Congbo Ma
Research Collection School Of Computing and Information Systems
Deep neural networks have gained great success in a broad range of tasks due to its remarkable capability to learn semantically rich features from high-dimensional data. However, they often require large-scale labelled data to successfully learn such features, which significantly hinders their adaption in unsupervised learning tasks, such as anomaly detection and clustering, and limits their applications to critical domains where obtaining massive labelled data is prohibitively expensive. To enable unsupervised learning on those domains, in this work we propose to learn features without using any labelled data by training neural networks to predict data distances in a randomly projected …
A Survey Of Enabling Technologies For Smart Communities,
2021
Old Dominion University
A Survey Of Enabling Technologies For Smart Communities, Amna Iqbal, Stephan Olariu
Computer Science Faculty Publications
In 2016, the Japanese Government publicized an initiative and a call to action for the implementation of a "Super Smart Society" announced as Society 5.0. The stated goal of Society 5.0 is to meet the various needs of the members of society through the provisioning of goods and services to those who require them, when they are required and in the amount required, thus enabling the citizens to live an active and comfortable life. In spite of its genuine appeal, details of a feasible path to Society 5.0 are conspicuously missing. The first main goal of this survey is to …
Using Eye-Gaze To Evaluate Neural Attention,
2020
Indian Statistical Institute
Using Eye-Gaze To Evaluate Neural Attention, Shahansha Salim
Master’s Dissertations
The ability to selectively concentrate on areas of interest while ignoring the rest is termed as attention in human beings. This ability has played a key role in survival as well as information processing. Neural Attention is said to be an effort to bring similar action of selectively concentrating areas of relevance in deep neural networks. This simple yet powerful concept has attracted a lot of research in recent years, yielding breakthrough results in Natural Language Processing (NLP) problems and main stream Computer Vision problems such as Image Caption Generation, Neural Machine Translation (NMT), Visual Question Answering (VQA), Action Recognition, …
Audee: Automated Testing For Deep Learning Frameworks,
2020
Singapore Management University
Audee: Automated Testing For Deep Learning Frameworks, Qianyu Guo, Xiaofei Xie, Yi Li, Xiaoyu Zhang, Yang Liu, Xiaohong Li, Chao Shen
Research Collection School Of Computing and Information Systems
Deep learning (DL) has been applied widely, and the quality of DL system becomes crucial, especially for safety-critical applications. Existing work mainly focuses on the quality analysis of DL models, but lacks attention to the underlying frameworks on which all DL models depend. In this work, we propose Audee, a novel approach for testing DL frameworks and localizing bugs. Audee adopts a search-based approach and implements three different mutation strategies to generate diverse test cases by exploring combinations of model structures, parameters, weights and inputs. Audee is able to detect three types of bugs: logical bugs, crashes and Not-a-Number (NaN) …
Lightweight Deep Learning For Botnet Ddos Detection On Iot Access Networks,
2020
Missouri State University
Lightweight Deep Learning For Botnet Ddos Detection On Iot Access Networks, Eric A. Mccullough
Graduate Theses/Dissertations
With the proliferation of the Internet of Things (IoT), computer networks have rapidly expanded in size. While Internet of Things Devices (IoTDs) benefit many aspects of life, these devices also introduce security risks in the form of vulnerabilities which give hackers billions of promising new targets. For example, botnets have exploited the security flaws common with IoTDs to gain unauthorized control of hundreds of thousands of hosts, which they then utilize to carry out massively disruptive distributed denial of service (DDoS) attacks. Traditional DDoS defense mechanisms rely on detecting attacks at their target and deploying mitigation strategies toward the attacker …
Watch Out! Motion Is Blurring The Vision Of Your Deep Neural Networks,
2020
Singapore Management University
Watch Out! Motion Is Blurring The Vision Of Your Deep Neural Networks, Qing Guo, Felix Juefei-Xu, Xiaofei Xie, Lei Ma, Jian Wang, Bing Yu, Wei Feng, Yang Liu
Research Collection School Of Computing and Information Systems
The state-of-the-art deep neural networks (DNNs) are vulnerable to adversarial examples with additive random noise-like perturbations. While such examples are hardly found in the physical world, the image blurring effect caused by object motion, on the other hand, commonly occurs in practice, making the study of which greatly important especially for the widely adopted real-time image processing tasks (e.g., object detection, tracking). In this paper, we initiate the first step to comprehensively investigate the potential hazards of blur effect for DNN, caused by object motion. We propose a novel adversarial attack method that can generate visually natural motion-blurred adversarial examples, …
Towards Theoretically Understanding Why Sgd Generalizes Better Than Adam In Deep Learning,
2020
Singapore Management University
Towards Theoretically Understanding Why Sgd Generalizes Better Than Adam In Deep Learning, Pan Zhou, Jiashi Feng, Chao Ma, Caiming Xiong, Steven C. H. Hoi, Weinan E
Research Collection School Of Computing and Information Systems
It is not clear yet why ADAM-alike adaptive gradient algorithms suffer from worse generalization performance than SGD despite their faster training speed. This work aims to provide understandings on this generalization gap by analyzing their local convergence behaviors. Specifically, we observe the heavy tails of gradient noise in these algorithms. This motivates us to analyze these algorithms through their Lévy-driven stochastic differential equations (SDEs) because of the similar convergence behaviors of an algorithm and its SDE. Then we establish the escaping time of these SDEs from a local basin. The result shows that (1) the escaping time of both SGD …
Sadt: Syntax-Aware Differential Testing Of Certificate Validation In Ssl/Tls Implementations,
2020
Singapore Management University
Sadt: Syntax-Aware Differential Testing Of Certificate Validation In Ssl/Tls Implementations, Lili Quan, Qianyu Guo, Hongxu Chen, Xiaofei Xie, Xiaohong Li, Yang Liu, Jing Hu
Research Collection School Of Computing and Information Systems
The security assurance of SSL/TLS critically depends on the correct validation of X.509 certificates. Therefore, it is important to check whether a certificate is correctly validated by the SSL/TLS implementations. Although differential testing has been proven to be effective in finding semantic bugs, it still suffers from the following limitations: (1) The syntax of test cases cannot be correctly guaranteed. (2) Current test cases are not diverse enough to cover more implementation behaviours. This paper tackles these problems by introducing SADT, a novel syntax-aware differential testing framework for evaluating the certificate validation process in SSL/TLS implementations. We first propose a …
Theory-Inspired Path-Regularized Differential Network Architecture Search,
2020
Singapore Management University
Theory-Inspired Path-Regularized Differential Network Architecture Search, Pan Zhou, Caiming Xiong, Richard Socher, Steven C. H. Hoi
Research Collection School Of Computing and Information Systems
Despite its high search efficiency, differential architecture search (DARTS) often selects network architectures with dominated skip connections which lead to performance degradation. However, theoretical understandings on this issue remain absent, hindering the development of more advanced methods in a principled way. In this work, we solve this problem by theoretically analyzing the effects of various types of operations, e.g. convolution, skip connection and zero operation, to the network optimization. We prove that the architectures with more skip connections can converge faster than the other candidates, and thus are selected by DARTS. This result, for the first time, theoretically and explicitly …
Cisc 4331 – Systems And Network Administration - Week 2,
2020
CUNY Brooklyn College
Cisc 4331 – Systems And Network Administration - Week 2, Jimmy Richford, Nyc Tech-In-Residence Corps
Open Educational Resources
Lecture 2 for CISC 4331: Systems and Network Administration
Systems And Network Administration - Introduction,
2020
CUNY Brooklyn College
Systems And Network Administration - Introduction, Jimmy Richford, Nyc Tech-In-Residence Corps
Open Educational Resources
Lecture for CISC 4311: Systems and Network Administration (Fall 2020)
Cisc 4331 – Systems And Network Administration - Week 5,
2020
CUNY Brooklyn College
Cisc 4331 – Systems And Network Administration - Week 5, Jimmy Richford, Nyc Tech-In-Residence Corps
Open Educational Resources
Lecture 5 for CISC 4331 - Systems and Network Administration
Cisc 4331 – Systems And Network Administration - Week 4,
2020
CUNY Brooklyn College
Cisc 4331 – Systems And Network Administration - Week 4, Jimmy Richford, Nyc Tech-In-Residence Corps
Open Educational Resources
Lecture 4 for CISC 4331 - Systems and Network Administration
Cisc 4331 – Systems And Network Administration - Week 3,
2020
CUNY Brooklyn College
Cisc 4331 – Systems And Network Administration - Week 3, Jimmy Richford, Nyc Tech-In-Residence Corps
Open Educational Resources
Lecture 3 for CISC 4331: Systems and Network Administration
Cisc 4331 – Systems And Network Administration Week 6,
2020
CUNY Brooklyn College
Cisc 4331 – Systems And Network Administration Week 6, Jimmy Richford, Nyc Tech-In-Residence Corps
Open Educational Resources
Lecture 6 for CISC 4331 - Systems and Network Administration
Lecture - Csci 275: Linux Systems Administration And Security,
2020
CUNY John Jay College
Lecture - Csci 275: Linux Systems Administration And Security, Moe Hassan, Nyc Tech-In-Residence Corps
Open Educational Resources
Lecture for CSCI 275: Linux Systems Administration and Security
Deepsonar: Towards Effective And Robust Detection Of Ai-Synthesized Fake Voices,
2020
Singapore Management University
Deepsonar: Towards Effective And Robust Detection Of Ai-Synthesized Fake Voices, Run Wang, Felix Juefei-Xu, Yihao Huang, Qing Guo, Xiaofei Xie, Lei Ma, Yang Liu
Research Collection School Of Computing and Information Systems
With the recent advances in voice synthesis, AI-synthesized fake voices are indistinguishable to human ears and widely are applied to produce realistic and natural DeepFakes, exhibiting real threats to our society. However, effective and robust detectors for synthesized fake voices are still in their infancy and are not ready to fully tackle this emerging threat. In this paper, we devise a novel approach, named DeepSonar, based on monitoring neuron behaviors of speaker recognition (SR) system, i.e., a deep neural network (DNN), to discern AI-synthesized fake voices. Layer-wise neuron behaviors provide an important insight to meticulously catch the differences among inputs, …
