Artificial Intelligence and Robotics Commons^™

Parallel Algorithms For Scalable Graph Mining: Applications On Big Data And Machine Learning, Naw Safrin Sattar

LSU New Orleans Theses and Dissertations

Parallel computing plays a crucial role in processing large-scale graph data. Complex network analysis is an exciting area of research for many applications in different scientific domains e.g., sociology, biology, online media, recommendation systems and many more. Graph mining is an area of interest with diverse problems from different domains of our daily life. Due to the advancement of data and computing technologies, graph data is growing at an enormous rate, for example, the number of links in social networks is growing every millisecond. Machine/Deep learning plays a significant role for technological accomplishments to work with big data in modern …

Directed Acyclic Graph-Based Neural Networks For Tunable Low-Power Computer Vision, Abhinav Goel, Caleb Tung, Nick Eliopoulos, Xiao Hu, George K. Thiruvathukal, James C. Davis, Yung-Hisang Lu

Computer Science: Faculty Publications and Other Works

Processing visual data on mobile devices has many applications, e.g., emergency response and tracking. State-of-the-art computer vision techniques rely on large Deep Neural Networks (DNNs) that are usually too power-hungry to be deployed on resource-constrained edge devices. Many techniques improve DNN efficiency of DNNs by compromising accuracy. However, the accuracy and efficiency of these techniques cannot be adapted for diverse edge applications with different hardware constraints and accuracy requirements. This paper demonstrates that a recent, efficient tree-based DNN architecture, called the hierarchical DNN, can be converted into a Directed Acyclic Graph-based (DAG) architecture to provide tunable accuracy-efficiency tradeoff options. We …

Distributed Learning With Automated Stepsizes, Benjamin Liggett

All Theses

Stepsizes for optimization problems play a crucial role in algorithm convergence, where the stepsize must undergo tedious manual tuning to obtain near-optimal convergence. Recently, an adaptive method for automating stepsizes was proposed for centralized optimization. However, this method is not directly applicable to decentralized optimization because it allows for heterogeneous agent stepsizes. Furthermore, directly using consensus between agent stepsizes to mitigate stepsize heterogeneity can decrease performance and even lead to divergence.

This thesis proposes an algorithm to remedy the tedious manual tuning of stepsizes in decentralized optimization. Our proposed algorithm automates the stepsize and uses dynamic consensus between agents’ stepsizes …

Unsupervised Contrastive Representation Learning For Knowledge Distillation And Clustering, Fei Ding

All Dissertations

Unsupervised contrastive learning has emerged as an important training strategy to learn representation by pulling positive samples closer and pushing negative samples apart in low-dimensional latent space. Usually, positive samples are the augmented versions of the same input and negative samples are from different inputs. Once the low-dimensional representations are learned, further analysis, such as clustering, and classification can be performed using the representations. Currently, there are two challenges in this framework. First, the empirical studies reveal that even though contrastive learning methods show great progress in representation learning on large model training, they do not work well for small …

Multi-Objective Evolutionary Algorithm Based On Rbf Network For Solving The Stochastic Vehicle Routing Problem, Yunyun Niu, Jie Shao, Jianhua Xiao, Wen Song, Zhiguang Cao

Research Collection School Of Computing and Information Systems

Solving the multi-objective vehicle routing problem with stochastic demand (MO-VRPSD) is challenging due to its non-deterministic property and conflicting objectives. Most multi -objective evolutionary algorithm dealing with this problem update current population without any guidance from previous searching experience. In this paper, a multi -objective evolutionary algorithm based on artificial neural networks is proposed to tackle the MO-VRPSD. Particularly, during the evolutionary process, a radial basis function net-work (RBFN) is exploited to learn the potential knowledge of individuals, generate hypoth-esis and instantiate hypothesis. The RBFN evaluates individuals with different scores and generates new individuals with higher quality while taking into …

Review Of Some Existing Qml Frameworks And Novel Hybrid Classical-Quantum Neural Networks Realising Binary Classification For The Noisy Datasets, N. Schetakis, D. Aghamalyan, Paul Robert Griffin, M. Boguslavsky

Research Collection School Of Computing and Information Systems

One of the most promising areas of research to obtain practical advantage is Quantum Machine Learning which was born as a result of cross-fertilisation of ideas between Quantum Computing and Classical Machine Learning. In this paper, we apply Quantum Machine Learning (QML) frameworks to improve binary classification models for noisy datasets which are prevalent in financial datasets. The metric we use for assessing the performance of our quantum classifiers is the area under the receiver operating characteristic curve AUC-ROC. By combining such approaches as hybrid-neural networks, parametric circuits, and data re-uploading we create QML inspired architectures and utilise them for …

Deep Learning For Anomaly Detection, Guansong Pang, Charu Aggarwal, Chunhua Shen, Nicu Sebe

Research Collection School Of Computing and Information Systems

A nomaly detection aims at identifying data points which are rare or significantly different from the majority of data points. Many techniques are explored to build highly efficient and effective anomaly detection systems, but they are confronted with many difficulties when dealing with complex data, such as failing to capture intricate feature interactions or extract good feature representations. Deep-learning techniques have shown very promising performance in tackling different types of complex data in a broad range of tasks/problems, including anomaly detection. To address this new trend, we organized this Special Issue on Deep Learning for Anomaly Detection to cover the …

Do-Gan: A Double Oracle Framework For Generative Adversarial Networks, Aye Phyu Phye Aung, Xinrun Wang, Runsheng Yu, Bo An, Senthilnath Jayavelu, Xiaoli Li

Research Collection School Of Computing and Information Systems

In this paper, we propose a new approach to train Gen-erative Adversarial Networks (GANs) where we deploy a double-oracle framework using the generator and discrim-inator oracles. GAN is essentially a two-player zero-sum game between the generator and the discriminator. Training GANs is challenging as a pure Nash equilibrium may not exist and even finding the mixed Nash equilibrium is difficult as GANs have a large-scale strategy space. In DO-GAN, we extend the double oracle framework to GANs. We first generalize the players' strategies as the trained models of generator and discriminator from the best response or-acles. We then compute the …

The Significance Of Sonic Branding To Strategically Stimulate Consumer Behavior: Content Analysis Of Four Interviews From Jeanna Isham’S “Sound In Marketing” Podcast, Ina Beilina

Student Theses and Dissertations

Purpose:
Sonic branding is not just about composing jingles like McDonald’s “I’m Lovin’ It.” Sonic branding is an industry that strategically designs a cohesive auditory component of a brand’s corporate identity. This paper examines the psychological impact of music and sound on consumer behavior reviewing studies from the past 40 years and investigates the significance of stimulating auditory perception by infusing sound in consumer experience in the modern 2020s.

Design/methodology/approach:
Qualitative content analysis of audio media was used to test two hypotheses. Four archival oral interview recordings from Jeanna Isham’s podcast “Sound in Marketing” featuring the sonic branding experts …

The Behaviors Of Bert Attention Heads In Stereotype Detection, Joseph H. Hajjar

Dartmouth College Master’s Theses

We are living in the age of information, where it has become increasingly easy to share ideas, news, and content which are seen by an increasingly large number of people. This increasing scope of the increasing amount of data that is being shared lends itself to the question: how can we determine whether what we are reading promotes a stereotype? Previous work has applied transformer based models in this domain yielding impressive performance, but few studies exist interpreting the nature of attention heads in this task. Our work explores the feature encoding and extraction behaviors of attention heads in transformer …

A Machine Learning And Deep Learning Framework For Binary, Ternary, And Multiclass Emotion Classification Of Covid-19 Vaccine-Related Tweets, Aditya Dubey

Honors Scholar Theses

My research mines public emotion toward the Covid-19 vaccine based on Twitter data collected over the past 6-12 months. This project is centered around building and developing machine learning and deep learning models to perform natural language processing of short-form text, which in our case tweets. These tweets are all vaccine-related tweets and the goal of the classification task is for our models to accurately classify a tweet into one of four emotion groups: Apprehension/Anticipation, Sadness/Anger/Frustration, Joy/Humor/Sarcasm, and Gratitude/Relief. Given this data and the goal of the paper, we aim to answer the following questions: (1) Can a framework be …

Gauging The State-Of-The-Art For Foresight Weight Pruning On Neural Networks, Noah James

Computer Science and Computer Engineering Undergraduate Honors Theses

The state-of-the-art for pruning neural networks is ambiguous due to poor experimental practices in the field. Newly developed approaches rarely compare to each other, and when they do, their comparisons are lackluster or contain errors. In the interest of stabilizing the field of pruning, this paper initiates a dive into reproducing prominent pruning algorithms across several architectures and datasets. As a first step towards this goal, this paper shows results for foresight weight pruning across 6 baseline pruning strategies, 5 modern pruning strategies, random pruning, and one legacy method (Optimal Brain Damage). All strategies are evaluated on 3 different architectures …

Data And Algorithmic Modeling Approaches To Count Data, Andraya Hack

Honors College Theses

Various techniques are used to create predictions based on count data. This type of data takes the form of a non-negative integers such as the number of claims an insurance policy holder may make. These predictions can allow people to prepare for likely outcomes. Thus, it is important to know how accurate the predictions are. Traditional statistical approaches for predicting count data include Poisson regression as well as negative binomial regression. Both methods also have a zero-inflated version that can be used when the data has an overabundance of zeros. Another procedure is to use computer algorithms, also known as …

Simulating Polistes Dominulus Nest-Building Heuristics With Deterministic And Markovian Properties, Benjamin Pottinger

Undergraduate Honors Theses

European Paper Wasps (Polistes dominula) are social insects that build round, symmetrical nests. Current models indicate that these wasps develop colonies by following simple heuristics based on nest stimuli. Computer simulations can model wasp behavior to imitate natural nest building. This research investigated various building heuristics through a novel Markov-based simulation. The simulation used a hexagonal grid to build cells based on the building rule supplied to the agent. Nest data was compared with natural data and through visual inspection. Larger nests were found to be less compact for the rules simulated.

The Executive’S Guide To Getting Ai Wrong, Jerrold Soh

Asian Management Insights

This article explores how we see AI and argues that we mostly get it wrong. In the process, it explains the reasons backed by social science research on why we tend to get AI wrong and illustrates the dangers of doing so from a managerial and law-making perspective. Some readers may also find the article useful as a guide on how and when to manipulate portrayals of AI in your favour.

Risk Gameplay Analysis Using Stochastic Beam Search, Jacob Gillenwater

Electronic Theses and Dissertations

Hasbro’s RISK, first published in 1959, is a complex multiplayer strategy game that has received little attention from the scientific community. Training artificial intelligence (AI) agents using stochastic beam search gives insight into effective strategy when playing RISK. A comprehensive analysis of the systems of play challenges preconceptions about good strategy in some areas of the game while reinforcing those preconceptions in others. This study applies stochastic beam search to discover optimal strategies in RISK. Results of the search show both support for and challenges to traditionally held positions about RISK gameplay. While stochastic beam search competently investigates gameplay on …

Neighborhood Cooperative Multiagent Reinforcement Learning For Adaptive Traffic Signal Control In Epidemic Regions, Chengwei Zhang, Yu Tian, Zhibin Zhang, Wanli Xue, Xiaofei Xie, Tianpei Yang, Xin Ge, Rong Chen

Research Collection School Of Computing and Information Systems

Nowadays, multiagent reinforcement learning (MARL) have shared significant advances in the adaptive traffic signal control (ATSC) problems. For most of the researches, agents are all isomorphic, which disregards the situation in which isomerous intersections cooperative together in a real ATSC scenario, especially in epidemic regions where different intersections have quite different levels of importance. To this end, this paper models the ATSC problem as a networked Markov game (NMG), in which agents take into account information, including traffic conditions of it and its connected neighbors. A cooperative MARL framework named neighborhood cooperative hysteretic DQN (NC-HDQN) is proposed. Specifically, for each …

Robust And Fair Machine Learning Under Distribution Shift, Wei Du

Graduate Theses and Dissertations

Machine learning algorithms have been widely used in real world applications. The development of these techniques has brought huge benefits for many AI-related tasks, such as natural language processing, image classification, video analysis, and so forth. In traditional machine learning algorithms, we usually assume that the training data and test data are independently and identically distributed (iid), indicating that the model learned from the training data can be well applied to the test data with good prediction performance. However, this assumption is quite restrictive because the distribution shift can exist from the training data to the test data in many …

Practical Considerations And Applications For Autonomous Robot Swarms, Rory Alan Hector

LSU Doctoral Dissertations

In recent years, the study of autonomous entities such as unmanned vehicles has begun to revolutionize both military and civilian devices. One important research focus of autonomous entities has been coordination problems for autonomous robot swarms. Traditionally, robot models are used for algorithms that account for the minimum specifications needed to operate the swarm. However, these theoretical models also gloss over important practical details. Some of these details, such as time, have been considered before (as epochs of execution). In this dissertation, we examine these details in the context of several problems and introduce new performance measures to capture practical …

Algorithm Selection For The Team Orienteering Problem, Mustafa Misir, Aldy Gunawan, Pieter Vansteenwegen

Research Collection School Of Computing and Information Systems

This work utilizes Algorithm Selection for solving the Team Orienteering Problem (TOP). The TOP is an NP-hard combinatorial optimization problem in the routing domain. This problem has been modelled with various extensions to address different real-world problems like tourist trip planning. The complexity of the problem motivated to devise new algorithms. However, none of the existing algorithms came with the best performance across all the widely used benchmark instances. This fact suggests that there is a performance gap to fill. This gap can be targeted by developing more new algorithms as attempted by many researchers before. An alternative strategy is …

Understanding The Mechanism Of Deep Learning Frameworks In Lesion Detection For Pathological Images With Breast Cancer, Wei-Wen Hsu, Chung-Hao Chen, Chang Hao, Yu-Ling Hou, Xiang Gao, Yun Shao, Xueli Zhang, Jingjing Wang, Tao He, Yanhong Tai

Electrical & Computer Engineering Faculty Publications

With the advances of scanning sensors and deep learning algorithms, computational pathology has drawn much attention in recent years and started to play an important role in the clinical workflow. Computer-aided detection (CADe) systems have been developed to assist pathologists in slide assessment, increasing diagnosis efficiency and reducing misdetections. In this study, we conducted four experiments to demonstrate that the features learned by deep learning models are interpretable from a pathological perspective. In addition, classifiers such as the support vector machine (SVM) and random forests (RF) were used in experiments to replace the fully connected layers and decompose the end-to-end …

Assessing Photogrammetry Artificial Intelligence In Monumental Buildings’ Crack Digital Detection, Said Maroun, Mostafa Khalifa, Nabil Mohareb

Architecture and Planning Journal (APJ)

Natural and human-made disasters have significant impacts on monumental buildings, threatening them from being deteriorated. If no rapid consolidations took into consideration traumatic accidents would endanger the existence of precious sites. In this context, Beirut's enormous 4th of August 2020 explosion damaged an estimated 640 historical monuments, many volunteers assess damages for more than a year to prevent the more crucial risk of demolitions. This research aims to assist the collaboration ability among photogrammetry science, Artificial Intelligence Model (AIM) and Architectural Coding to optimize the process for better coverage and scientific approach of data specific to the crack disorders to …

The Global Rise Of Online Devices, Cyber Crime And Cyber Defense: Enhancing Ethical Actions, Counter Measures, Cyber Strategy, And Approaches, Naresh Kshetri

Dissertations

The rise of online devices, online users, online shopping, online gaming, and online teaching has ultimately given rise to online attacks and online crimes. As cases of COVID-19 seem to increase day by day, so do online crimes and attacks (as many sectors and organizations went 100% online). Technological advancements and cyber warfare already generated many ethical issues, as internet users increasingly need ethical cyber defense strategies.

Individual internet users have challenges on their end; and on the other end, nation states (some secretly, some openly), are investing in robot weapons and autonomous weapons systems (AWS). New technologies have combined …

The Effect Of Using The Gamification Strategy On Academic Achievement And Motivation Towards Learning Problem-Solving Skills In Computer And Information Technology Course Among Tenth Grade Female Students, Mazyunah Almutairi, Prof. Ahmad Almassaad

International Journal for Research in Education

Abstract

This study aimed to identify the effect of using the gamification strategy on academic achievement and motivation towards learning problem-solving skills in computer and information technology course. A quasi-experimental method was adopted. The study population included tenth-grade female students in Al-Badi’ah schools in Riyadh. The sample consisted of 54 students divided into two equal groups: control group and experimental group. The study tools comprised an achievement test and the motivation scale. The results showed that there were statistically significant differences between the two groups in the academic achievement test in favor of the experimental group, with a large effect …

Mitigation Of Algorithmic Bias To Improve Ai Fairness, Kathy Wang

Cybersecurity Undergraduate Research Showcase

As artificial intelligence continues to evolve rapidly with emerging innovations, mass-scale digitization could be disrupted due to unfair algorithms with historically biased data. With the rising concerns of algorithmic bias, detecting biases is essential in mitigating and implementing an algorithm that promotes inclusive representation. The spread of ubiquitous artificial intelligence means that improving modeling robustness is at its most crucial point. This paper examines the omnipotence of artificial intelligence and its resulting bias, examples of AI bias in different groups, and a potential framework and mitigation strategies to improve AI fairness and remove AI bias from modeling techniques.

A Comparison Of Deep Learning Algorithms On Image Data For Detecting Floodwater On Roadways, Sarp Salih, Kuzlu Murat, Zhao Yanxiao, Cetin Mecit

Engineering Technology Faculty Publications

Object detection and segmentation algorithms evolved significantly in the last decade. Simultaneous object detection and segmentation paved the way for real-time applications such as autonomous driving. Detection and segmentation of (partially) flooded roadways are essential inputs for vehicle routing and traffic management systems. This paper proposes an automatic floodwater detection and segmentation method utilizing the Mask Region-Based Convolutional Neural Networks (Mask-R-CNN) and Generative Adversarial Networks (GAN) algorithms. To train the model, manually labeled images with urban, suburban, and natural settings are used. The performances of the algorithms are assessed in accurately detecting the floodwater captured in images. The results show …

The Performance Optimization Of Asp Solving Based On Encoding Rewriting And Encoding Selection, Liu Liu

Theses and Dissertations--Computer Science

Answer set programming (ASP) has long been used for modeling and solving hard search problems. These problems are modeled in ASP as encodings, a collection of rules that declaratively describe the logic of the problem without explicitly listing how to solve it. It is common that the same problem has several different but equivalent encodings in ASP. Experience shows that the performance of these ASP encodings may vary greatly from instance to instance when processed by current state-of-the-art ASP grounder/solver systems. In particular, it is rarely the case that one encoding outperforms all others. Moreover, running an ASP system on …

Interpretable Design Of Reservoir Computing Networks Using Realization Theory, Wei Miao, Vignesh Narayanan, Jr-Shin Li

Publications

The reservoir computing networks (RCNs) have been successfully employed as a tool in learning and complex decision-making tasks. Despite their efficiency and low training cost, practical applications of RCNs rely heavily on empirical design. In this article, we develop an algorithm to design RCNs using the realization theory of linear dynamical systems. In particular, we introduce the notion of α-stable realization and provide an efficient approach to prune the size of a linear RCN without deteriorating the training accuracy. Furthermore, we derive a necessary and sufficient condition on the irreducibility of the number of hidden nodes in linear RCNs based …

Reinforcement Learning Applied To The Shoals Marine Laboratory Smart Grid, Daniel C. Mattson

Honors Theses and Capstones

Reinforcement learning (RL) techniques have been applied to smart grids with a variety of applications. The most common objective is to optimize profit for one actor in the system. The goal of this work is to apply different RL models to the smart grid at the Shoals Marine Laboratory (SML) located on Appledore Island, Maine in an effort to reduce costs and minimize the amount of nonrenewable energy consumed on the island. The RL models implemented resulted in more sustainable practices in simulations, with a linear spline model outperforming the naive policy the SML currently uses. Future work includes extending …

A Synthetic Prediction Market For Estimating Confidence In Published Work, Sarah Rajtmajer, Christopher Griffin, Jian Wu, Robert Fraleigh, Laxmann Balaji, Anna Squicciarini, Anthony Kwasnica, David Pennock, Michael Mclaughlin, Timothy Fritton, Nishanth Nakshatri, Arjun Menon, Sai Ajay Modukuri, Rajal Nivargi, Xin Wei, Lee Giles

Computer Science Faculty Publications

[First paragraph] Concerns about the replicability, robustness and reproducibility of findings in scientific literature have gained widespread attention over the last decade in the social sciences and beyond. This attention has been catalyzed by and has likewise motivated a number of large-scale replication projects which have reported successful replication rates between 36% and 78%. Given the challenges and resources required to run high-powered replication studies, researchers have sought other approaches to assess confidence in published claims. Initial evidence has supported the promise of prediction markets in this context. However, they require the coordinated, sustained effort of collections of human experts …