Artificial Intelligence and Robotics Commons^™

Fine-Grained Generalization Analysis Of Vector-Valued Learning, Liang Wu, Antoine Ledent, Yunwen Lei, Marius Kloft

Research Collection School Of Computing and Information Systems

Many fundamental machine learning tasks can be formulated as a problem of learning with vector-valued functions, where we learn multiple scalar-valued functions together. Although there is some generalization analysis on different specific algorithms under the empirical risk minimization principle, a unifying analysis of vector-valued learning under a regularization framework is still lacking. In this paper, we initiate the generalization analysis of regularized vector-valued learning algorithms by presenting bounds with a mild dependency on the output dimension and a fast rate on the sample size. Our discussions relax the existing assumptions on the restrictive constraint of hypothesis spaces, smoothness of loss …

Using Torchattacks To Improve The Robustness Of Models With Adversarial Training, William S. Matos Díaz

Cybersecurity: Deep Learning Driven Cybersecurity Research in a Multidisciplinary Environment

Adversarial training has proven to be one of the most successful ways to defend models against adversarial examples. This process consists of training a model with an adversarial example to improve the robustness of the model. In this experiment, Torchattacks, a Pytorch library made for importing adversarial examples more easily, was used to determine which attack was the strongest. Later on, the strongest attack was used to train the model and make it more robust against adversarial examples. The datasets used to perform the experiments were MNIST and CIFAR-10. Both datasets were put to the test using PGD, FGSM, and …

Representing And Learning Preferences Over Combinatorial Domains, Michael Huelsman

Theses and Dissertations--Computer Science

Agents make decisions based on their preferences. Thus, to predict their decisions one has to learn the agent's preferences. A key step in the learning process is selecting a model to represent those preferences. We studied this problem by borrowing techniques from the algorithm selection problem to analyze preference example sets and select the most appropriate preference representation for learning. We approached this problem in multiple steps.

First, we determined which representations to consider. For this problem we developed the notion of preference representation language subsumption, which compares representations based on their expressive power. Subsumption creates a hierarchy of preference …

Learning From Multi-Class Imbalanced Big Data With Apache Spark, William C. Sleeman Iv

Theses and Dissertations

With data becoming a new form of currency, its analysis has become a top priority in both academia and industry, furthering advancements in high-performance computing and machine learning. However, these large, real-world datasets come with additional complications such as noise and class overlap. Problems are magnified when with multi-class data is presented, especially since many of the popular algorithms were originally designed for binary data. Another challenge arises when the number of examples are not evenly distributed across all classes in a dataset. This often causes classifiers to favor the majority class over the minority classes, leading to undesirable results …

Scaling Up Exact Neural Network Compression By Relu Stability, Thiago Serra, Xin Yu, Abhinav Kumar, Srikumar Ramalingam

Faculty Conference Papers and Presentations

We can compress a rectifier network while exactly preserving its underlying functionality with respect to a given input domain if some of its neurons are stable. However, current approaches to determine the stability of neurons with Rectified Linear Unit (ReLU) activations require solving or finding a good approximation to multiple discrete optimization problems. In this work, we introduce an algorithm based on solving a single optimization problem to identify all stable neurons. Our approach is on median 183 times faster than the state-of-art method on CIFAR-10, which allows us to explore exact compression on deeper (5 x 100) and wider …

A Novel Dimensionality Reduction Approach To Improve Microarray Data Classification, Mohammed Hasim, Ismail El Mouden, Mounir Ouzir, Hicham Moutachaouik, Mustapha Hain

Department of Medicine Faculty Publications

Cancer tumor prediction and diagnosis at an early stage has become a necessity in cancer research, as it provides an increase in the treatment success chances. Recently, DNA microarray technology became a powerful tool for cancer identification, that can analyze the expression level of a different and huge number of genes simultaneously. In microarray data, the large genes number versus a few records may affect the prediction performance. In order to handle this "curse of dimensionality” constraint of microarray dataset while improving the cancer identification performance, a dimensional reduction phase is necessary. In this paper, we proposed a framework that …

Partial Adversarial Behavior Deception In Security Games, Thanh H. Nguyen, Arunesh Sinha, He He

Research Collection School Of Computing and Information Systems

Learning attacker behavior is an important research topic in security games as security agencies are often uncertain about attackers’ decision making. Previous work has focused on developing various behavioral models of attackers based on historical attack data. However, a clever attacker can manipulate its attacks to fail such attack-driven learning, leading to ineffective defense strategies. We study attacker behavior deception with three main contributions. First, we propose a new model, named partial behavior deception model, in which there is a deceptive attacker (among multiple attackers) who controls a portion of attacks. Our model captures real-world security scenarios such as wildlife …

Ssentiaa: A Self-Supervised Sentiment Analyzer For Classification From Unlabeled Data, Salim Sazzed, Sampath Jayarathna

Computer Science Faculty Publications

In recent years, supervised machine learning (ML) methods have realized remarkable performance gains for sentiment classification utilizing labeled data. However, labeled data are usually expensive to obtain, thus, not always achievable. When annotated data are unavailable, the unsupervised tools are exercised, which still lag behind the performance of supervised ML methods by a large margin. Therefore, in this work, we focus on improving the performance of sentiment classification from unlabeled data. We present a self-supervised hybrid methodology SSentiA (Self-supervised Sentiment Analyzer) that couples an ML classifier with a lexicon-based method for sentiment classification from unlabeled data. We first introduce LRSentiA …

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, …

New Methods For Deep Learning Based Real-Valued Inter-Residue Distance Prediction, Jacob Barger

Theses

Background: Much of the recent success in protein structure prediction has been a result of accurate protein contact prediction--a binary classification problem. Dozens of methods, built from various types of machine learning and deep learning algorithms, have been published over the last two decades for predicting contacts. Recently, many groups, including Google DeepMind, have demonstrated that reformulating the problem as a multi-class classification problem is a more promising direction to pursue. As an alternative approach, we recently proposed real-valued distance predictions, formulating the problem as a regression problem. The nuances of protein 3D structures make this formulation appropriate, allowing predictions …

Espade: An Efficient And Semantically Secure Shortest Path Discovery For Outsourced Location-Based Services, Bharath K. Samanthula, Divyadharshini Karthikeyan, Boxiang Dong, K. Anitha Kumari

Department of Computer Science Faculty Scholarship and Creative Works

With the rapid growth of smart devices and technological advancements in tracking geospatial data, the demand for Location-Based Services (LBS) is facing a constant rise in several domains, including military, healthcare and transportation. It is a natural step to migrate LBS to a cloud environment to achieve on-demand scalability and increased resiliency. Nonetheless, outsourcing sensitive location data to a third-party cloud provider raises a host of privacy concerns as the data owners have reduced visibility and control over the outsourced data. In this paper, we consider outsourced LBS where users want to retrieve map directions without disclosing their location information. …

Reinforcement Learning For Zone Based Multiagent Pathfinding Under Uncertainty, Jiajing Ling, Tarun Gupta, Akshat Kumar

Research Collection School Of Computing and Information Systems

We address the problem of multiple agents finding their paths from respective sources to destination nodes in a graph (also called MAPF). Most existing approaches assume that all agents move at fixed speed, and that a single node accommodates only a single agent. Motivated by the emerging applications of autonomous vehicles such as drone traffic management, we present zone-based path finding (or ZBPF) where agents move among zones, and agents' movements require uncertain travel time. Furthermore, each zone can accommodate multiple agents (as per its capacity). We also develop a simulator for ZBPF which provides a clean interface from the …

F-Measure Optimisation And Label Regularisation For Energy-Based Neural Dialogue State Tracking Models, Anh Duong Trinh, Robert J. Ross, John D. Kelleher

Conference papers

In recent years many multi-label classification methods have exploited label dependencies to improve performance of classification tasks in various domains, hence casting the tasks to structured prediction problems. We argue that multi-label predictions do not always satisfy domain constraint restrictions. For example when the dialogue state tracking task in task-oriented dialogue domains is solved with multi-label classification approaches, slot-value constraint rules should be enforced following real conversation scenarios.

To address these issues we propose an energy-based neural model to solve the dialogue state tracking task as a structured prediction problem. Furthermore we propose two improvements over previous methods with respect …

A 3d Image-Guided System To Improve Myocardial Revascularization Decision-Making For Patients With Coronary Artery Disease, Haipeng Tang

Dissertations

OBJECTIVES. Coronary artery disease (CAD) is the most common type of heart disease and kills over 360,000 people a year in the United States. Myocardial revascularization (MR) is a standard interventional treatment for patients with stable CAD. Fluoroscopy angiography is real-time anatomical imaging and routinely used to guide MR by visually estimating the percent stenosis of coronary arteries. However, a lot of patients do not benefit from the anatomical information-guided MR without functional testing. Single-photon emission computed tomography (SPECT) myocardial perfusion imaging (MPI) is a widely used functional testing for CAD evaluation but limits to the absence of anatomical information. …

Unsupervised Monocular Depth Estimation With Multi-Scale Structural Similarity Powered Loss Function, Kohan Ali

Student Works (2020-2029)

Depth Estimation refers to a set of techniques and algorithms that aim to obtain a representation of spatial information of a scene. Nowadays specific hardware such as sensors, radars and multiple-view-recording cameras are being used in order to acquire depth data of a scene. Modern approaches use deep learning to address this task by trying to learn depth information in a supervised manner. However, this approach requires a large amount ground-truth data for a particular scene so that a model can be trained successfully. Also preparing ground-truth data for a range of environments is a challenging and expensive task to …

Efficient Vehicle Routing Optimization For Autistic Users, Mohammed Shabalah Abdulrahman Hasan

Student Works (2020-2029)

In recent years, daily life without a vehicle would be impossible. As an inevitable result, the number of vehicles on the road increases day by day in various large cities around the world. The increased number of vehicles is a big concern because it causes a lot of traffic congestions, especially during peak hours. Besides, there has been a rapid rise of on-demand Ride-Hailing Services (RHSs), such as Grab, Uber, EzCab, and MyCar, etc. This allows passengers with smartphones to place trip requests and assign them to drivers according to requester’s location and drivers' availability. In consequence, efficient routing algorithms …

Query Graph Generation For Answering Multi-Hop Complex Questions From Knowledge Bases, Yunshi Lan, Jing Jiang

Research Collection School Of Computing and Information Systems

Previous work on answering complex questions from knowledge bases usually separately addresses two types of complexity: questions with constraints and questions with multiple hops of relations. In this paper, we handle both types of complexity at the same time. Motivated by the observation that early incorporation of constraints into query graphs can more effectively prune the search space, we propose a modified staged query graph generation method with more flexible ways to generate query graphs. Our experiments clearly show that our method achieves the state of the art on three benchmark KBQA datasets.

Translating Counting Problems Into Computable Language Expressions, Zach Prescott

Theses

The realm of automated problem solving is a relatively new field, even in the context of natural language processing. One area where this is often demonstrated is that of creating a program that can solve word problems. The program must understand the problem, perform some processing, and then convey this information to a user in a way that is accessible and understandable. There has been quite a lot of progress in this area with simpler problems. However, when it comes to understanding problems that involve a level of NLP, the results are not conclusive. In this paper, we would like …

Evaluating Driving Performance Of A Novel Behavior Planning Model On Connected Autonomous Vehicles, Keyur Shah

Honors Scholar Theses

Many current algorithms and approaches in autonomous driving attempt to solve the "trajectory generation" or "trajectory following” problems: given a target behavior (e.g. stay in the current lane at the speed limit or change lane), what trajectory should the vehicle follow, and what inputs should the driving agent apply to the throttle and brake to achieve this trajectory? In this work, we instead focus on the “behavior planning” problem—specifically, should an autonomous vehicle change lane or keep lane given the current state of the system?

In addition, current theory mainly focuses on single-vehicle systems, where vehicles do not communicate with …

Predictive Modeling Of Asynchronous Event Sequence Data, Jin Shang

LSU Doctoral Dissertations

Large volumes of temporal event data, such as online check-ins and electronic records of hospital admissions, are becoming increasingly available in a wide variety of applications including healthcare analytics, smart cities, and social network analysis. Those temporal events are often asynchronous, interdependent, and exhibiting self-exciting properties. For example, in the patient's diagnosis events, the elevated risk exists for a patient that has been recently at risk. Machine learning that leverages event sequence data can improve the prediction accuracy of future events and provide valuable services. For example, in e-commerce and network traffic diagnosis, the analysis of user activities can be …

Applying Imitation And Reinforcement Learning To Sparse Reward Environments, Haven Brown

Computer Science and Computer Engineering Undergraduate Honors Theses

The focus of this project was to shorten the time it takes to train reinforcement learning agents to perform better than humans in a sparse reward environment. Finding a general purpose solution to this problem is essential to creating agents in the future capable of managing large systems or performing a series of tasks before receiving feedback. The goal of this project was to create a transition function between an imitation learning algorithm (also referred to as a behavioral cloning algorithm) and a reinforcement learning algorithm. The goal of this approach was to allow an agent to first learn to …

Achieving Causal Fairness In Machine Learning, Yongkai Wu

Graduate Theses and Dissertations

Fairness is a social norm and a legal requirement in today's society. Many laws and regulations (e.g., the Equal Credit Opportunity Act of 1974) have been established to prohibit discrimination and enforce fairness on several grounds, such as gender, age, sexual orientation, race, and religion, referred to as sensitive attributes. Nowadays machine learning algorithms are extensively applied to make important decisions in many real-world applications, e.g., employment, admission, and loans. Traditional machine learning algorithms aim to maximize predictive performance, e.g., accuracy. Consequently, certain groups may get unfairly treated when those algorithms are applied for decision-making. Therefore, it is an imperative …

A Matheuristic Algorithm For Solving The Vehicle Routing Problem With Cross-Docking, Aldy Gunawan, Audrey Tedja Widjaja, Pieter Vansteenwegen, Vincent F. Yu

Research Collection School Of Computing and Information Systems

This paper studies the integration of the vehicle routing problem with cross-docking, namely VRPCD. The aim is to find a set of routes to deliver single products from a set of suppliers to a set of customers through a cross-dock facility, such that the operational and transportation costs are minimized, without violating the vehicle capacity and time horizon constraints. A two-phase matheuristic approach that uses the routes of the local optima of an adaptive large neighborhood search (ALNS) as columns in a set-partitioning formulation of the VRPCD is designed. This matheuristic outperforms the state-of-the-art algorithms in solving a subset of …

Improving Syntactic Relationships Between Language And Objects, Benjamin Wilke, Tej Tenmattam, Anand Rajan, Andrew Pollock, Joel Lindsey

SMU Data Science Review

This paper presents the integration of natural language processing and computer vision to improve the syntax of the language generated when describing objects in images. The goal was to not only understand the objects in an image, but the interactions and activities occurring between the objects. We implemented a multi-modal neural network combining convolutional and recurrent neural network architectures to create a model that can maximize the likelihood of word combinations given a training image. The outcome was an image captioning model that leveraged transfer learning techniques for architecture components. Our novelty was to quantify the effectiveness of transfer learning …

Achieving Obfuscation Through Self-Modifying Code: A Theoretical Model, Heidi Waddell

Senior Honors Theses

With the extreme amount of data and software available on networks, the protection of online information is one of the most important tasks of this technological age. There is no such thing as safe computing, and it is inevitable that security breaches will occur. Thus, security professionals and practices focus on two areas: security, preventing a breach from occurring, and resiliency, minimizing the damages once a breach has occurred. One of the most important practices for adding resiliency to source code is through obfuscation, a method of re-writing the code to a form that is virtually unreadable. …

Storage Management Strategy In Mobile Phones For Photo Crowdsensing, En Wang, Zhengdao Qu, Xinyao Liang, Xiangyu Meng, Yongjian Yang, Dawei Li, Weibin Meng

Department of Computer Science Faculty Scholarship and Creative Works

In mobile crowdsensing, some users jointly finish a sensing task through the sensors equipped in their intelligent terminals. In particular, the photo crowdsensing based on Mobile Edge Computing (MEC) collects pictures for some specific targets or events and uploads them to nearby edge servers, which leads to richer data content and more efficient data storage compared with the common mobile crowdsensing; hence, it has attracted an important amount of attention recently. However, the mobile users prefer uploading the photos through Wifi APs (PoIs) rather than cellular networks. Therefore, photos stored in mobile phones are exchanged among users, in order to …

A Semi-Automatic Integrated Framework For Non-English Sentiment Lexicons, Abdullah Kaity Mohammed Salem

Student Works (2020-2029)

There has been significant growth in social media networks in the last few years. Posting opinions and messages on social networking websites has become a popular activity on the Internet. The data sources are necessary for business intelligence and market analytics, as human opinions form a major indicator of human desires and behaviour. This has resulted in the development of a new study field called sentiment analysis. This includes the analysis, evaluation and interpretation of the opinions with the help of text mining and Natural Language Processing (NLP) processes, for identifying the text polarity, as positive, neutral or negative. It …

Multi-Tier Classification Based On Sentiment, Type, Emotion And Purpose For Online Diabetes Community, Ratan Singh Wandeep Kaur

Student Works (2020-2029)

The evolution of social media platforms has created a niche for users to increasingly turn to such sites in order to share and exchange health related information. Facebook being one of the largest social networking sites has only encouraged such exchange thus mounting to a sheer amount of data that is hidden within unstructured text. The aim of this research is to propose a multi-tier classification based on sentiment, type, emotion and purpose (STEP) to classify data collected from diabetes community within Facebook. There are three tiers within the proposed STEP framework namely type, purpose and sentiment (and emotion within …

Neural Network Pruning For Ecg Arrhythmia Classification, Isaac E. Labarge

Master's Theses

Convolutional Neural Networks (CNNs) are a widely accepted means of solving complex classification and detection problems in imaging and speech. However, problem complexity often leads to considerable increases in computation and parameter storage costs. Many successful attempts have been made in effectively reducing these overheads by pruning and compressing large CNNs with only a slight decline in model accuracy. In this study, two pruning methods are implemented and compared on the CIFAR-10 database and an ECG arrhythmia classification task. Each pruning method employs a pruning phase interleaved with a finetuning phase. It is shown that when performing the scale-factor pruning …

Bounding Regret In Empirical Games, Steven Jecmen, Arunesh Sinha, Zun Li, Long Tran-Thanh

Research Collection School Of Computing and Information Systems

Empirical game-theoretic analysis refers to a set of models and techniques for solving large-scale games. However, there is a lack of a quantitative guarantee about the quality of output approximate Nash equilibria (NE). A natural quantitative guarantee for such an approximate NE is the regret in the game (i.e. the best deviation gain). We formulate this deviation gain computation as a multi-armed bandit problem, with a new optimization goal unlike those studied in prior work. We propose an efficient algorithm Super-Arm UCB (SAUCB) for the problem and a number of variants. We present sample complexity results as well as extensive …