Artificial Intelligence and Robotics Commons^™

Dilf: Differentiable Rendering-Based Multi-View Image-Language Fusion For Zero-Shot 3d Shape Understanding, Xin Ning, Zaiyang Yu, Lusi Li, Weijun Li, Prayag Tiwari

Computer Science Faculty Publications

Zero-shot 3D shape understanding aims to recognize “unseen” 3D categories that are not present in training data. Recently, Contrastive Language–Image Pre-training (CLIP) has shown promising open-world performance in zero-shot 3D shape understanding tasks by information fusion among language and 3D modality. It first renders 3D objects into multiple 2D image views and then learns to understand the semantic relationships between the textual descriptions and images, enabling the model to generalize to new and unseen categories. However, existing studies in zero-shot 3D shape understanding rely on predefined rendering parameters, resulting in repetitive, redundant, and low-quality views. This limitation hinders the model’s …

Perception Of Bias In Chatgpt: Analysis Of Social Media Data, Abdullah Wahbeh, Mohammad A. Al-Ramahi, Omar El-Gayar, Ahmed El Noshokaty, Tareq Nasralah

Computer Information Systems Faculty Publications

In this study, we aim to analyze the public perception of Twitter users with respect to the use of ChatGPT and the potential bias in its responses. Sentiment and emotion analysis were also analyzed. Analysis of 5,962 English tweets showed that Twitter users were concerned about six main types of biases, namely: political, ideological, data & algorithmic, gender, racial, cultural, and confirmation biases. Sentiment analysis showed that most of the users reflected a neutral sentiment, followed by negative and positive sentiment. Emotion analysis mainly reflected anger, disgust, and sadness with respect to bias concerns with ChatGPT use.

Estimating Propensity For Causality-Based Recommendation Without Exposure Data, Zhongzhou Liu, Yuan Fang, Min Wu

Research Collection School Of Computing and Information Systems

Causality-based recommendation systems focus on the causal effects of user-item interactions resulting from item exposure (i.e., which items are recommended or exposed to the user), as opposed to conventional correlation-based recommendation. They are gaining popularity due to their multi-sided benefits to users, sellers and platforms alike. However, existing causality-based recommendation methods require additional input in the form of exposure data and/or propensity scores (i.e., the probability of exposure) for training. Such data, crucial for modeling causality in recommendation, are often not available in real-world situations due to technical or privacy constraints. In this paper, we bridge the gap by proposing …

General Population Projection Model With Census Population Data, Takenori Tsuruga

Electronic Theses, Projects, and Dissertations

The US Census Bureau offers a wide range of data, and within this array, the American Community Survey 5-Year Estimate (ACS5) serves as a valuable resource for understanding the US population. This project embarks on an exploration of Machine Learning and the Software Development process with the goal of generating effective population projections from ACS5 data. The project aims to provide methods to make predictions for every city and town in the US, encompassing their total population and population divided into 5-year age groups. It's worth noting that while the generation of these projections is grounded in the generalized statistical …

Disease Of Lung Infection Detection Using Cnn Model -Bayesian Optimization, Poojitha Gutha

Electronic Theses, Projects, and Dissertations

Auscultation plays a role, in diagnosing and identifying diseases during examinations. However, it requires training and expertise, for application. This study aims to tackle this challenge by introducing a model that categorizes respiratory sounds into eight groups: URTI, Healthy, Asthma, COPD, LRTI, Bronchiectasis, Pneumonia, and Bronchiolitis. To achieve this categorization the study utilizes a Convolutional Neural Network (CNN) model that has been optimized using techniques. The dataset used in the study consists of 920 audio samples obtained from 126 patients with durations ranging from 10 to 90 seconds. Impressively, the model demonstrates a noteworthy 83% validation accuracy and an impressive …

Explainable Artificial Intelligence: Approaching It From The Lowest Level, Ralf P. Riedel

Theses and Dissertations

The increasing complexity of artificial intelligence models has given rise to extensive work toward understanding the inner workings of neural networks. Much of that work, however, has focused on manipulating input data feeding the network to assess their affects on network output or pruning model components after the often-extensive time-consuming training. It is postulated in this study that understanding of neural network can benefit from model structure simplification. In turn, it is shown that model simplification can benefit from investigating network node, the most fundamental unit of neural networks, evolving trends during training. Whereas studies on simplification of model structure …

Machine Learning In Minecraft: Proof Of Concept For Object Detection Oriented Autonomous Bots In Minecraft, John Merkin

Symposium of Student Scholars

Machine learning provides new methods of problem solving through applied pattern recognition. An interesting challenge is to utilize machine learning in the automation of tasks and behaviors in virtual environments. Minecraft is an open-world, sandbox style game giving players nearly limitless freedom to alter a procedurally generated world. In the survival game mode, the player must collect resources to craft tools and build structures. The collection of resources can be tedious, so this project seeks to automate the standard initial task of collecting wood. By combining a convolutional neural network with API, a bot can collect resources while remaining scalable …

Toxic Comment Classification Project, Brandon Solon

Symposium of Student Scholars

The digital landscape has blossomed thanks to the surge of online platforms, boosting the variety and volume of user-created content. But it's not without its shadows; cyberbullying and hate speech have also proliferated, making web spaces less safe. At our project centerstage, we work on creating a machine learning model skilled at spotting toxic comments with precision - this way contributing towards an internet society free from fear or discomfort. We put well-documented datasets to good use along with careful preprocessing maneuvers while trialing diverse machina-learning protocols as part of constructing solid classification architecture for usages beyond current limitations within …

Integrity, Confidentiality, And Equity: Using Inquiry-Based Labs To Help Students Understand Ai And Cybersecurity, Richard C. Alexander, Liran Ma, Ze-Li Dou, Zhipeng Cai, Yan Huang

Journal of Cybersecurity Education, Research and Practice

Recent advances in Artificial Intelligence (AI) have brought society closer to the long-held dream of creating machines to help with both common and complex tasks and functions. From recommending movies to detecting disease in its earliest stages, AI has become an aspect of daily life many people accept without scrutiny. Despite its functionality and promise, AI has inherent security risks that users should understand and programmers must be trained to address. The ICE (integrity, confidentiality, and equity) cybersecurity labs developed by a team of cybersecurity researchers addresses these vulnerabilities to AI models through a series of hands-on, inquiry-based labs. Through …

Towards Robust Long-Form Text Generation Systems, Kalpesh Krishna

Doctoral Dissertations

Text generation is an important emerging AI technology that has seen significant research advances in recent years. Due to its closeness to how humans communicate, mastering text generation technology can unlock several important applications such as intelligent chat-bots, creative writing assistance, or newer applications like task-agnostic few-shot learning. Most recently, the rapid scaling of large language models (LLMs) has resulted in systems like ChatGPT, capable of generating fluent, coherent and human-like text. However, despite their remarkable capabilities, LLMs still suffer from several limitations, particularly when generating long-form text. In particular, (1) long-form generated text is filled with factual inconsistencies to …

Quantifying And Enhancing The Security Of Federated Learning, Virat Vishnu Shejwalkar

Doctoral Dissertations

Federated learning is an emerging distributed learning paradigm that allows multiple users to collaboratively train a joint machine learning model without having to share their private data with any third party. Due to many of its attractive properties, federated learning has received significant attention from academia as well as industry and now powers major applications, e.g., Google's Gboard and Assistant, Apple's Siri, Owkin's health diagnostics, etc. However, federated learning is yet to see widespread adoption due to a number of challenges. One such challenge is its susceptibility to poisoning by malicious users who aim to manipulate the joint machine learning …

Learning To See With Minimal Human Supervision, Zezhou Cheng

Doctoral Dissertations

Deep learning has significantly advanced computer vision in the past decade, paving the way for practical applications such as facial recognition and autonomous driving. However, current techniques depend heavily on human supervision, limiting their broader deployment. This dissertation tackles this problem by introducing algorithms and theories to minimize human supervision in three key areas: data, annotations, and neural network architectures, in the context of various visual understanding tasks such as object detection, image restoration, and 3D generation.

First, we present self-supervised learning algorithms to handle in-the-wild images and videos that traditionally require time-consuming manual curation and labeling. We demonstrate that …

Foundations Of Node Representation Learning, Sudhanshu Chanpuriya

Doctoral Dissertations

Low-dimensional node representations, also called node embeddings, are a cornerstone in the modeling and analysis of complex networks. In recent years, advances in deep learning have spurred development of novel neural network-inspired methods for learning node representations which have largely surpassed classical 'spectral' embeddings in performance. Yet little work asks the central questions of this thesis: Why do these novel deep methods outperform their classical predecessors, and what are their limitations?

We pursue several paths to answering these questions. To further our understanding of deep embedding methods, we explore their relationship with spectral methods, which are better understood, and show …

Bayesian Structural Causal Inference With Probabilistic Programming, Sam A. Witty

Doctoral Dissertations

Reasoning about causal relationships is central to the human experience. This evokes a natural question in our pursuit of human-like artificial intelligence: how might we imbue intelligent systems with similar causal reasoning capabilities? Better yet, how might we imbue intelligent systems with the ability to learn cause and effect relationships from observation and experimentation? Unfortunately, reasoning about cause and effect requires more than just data: it also requires partial knowledge about data generating mechanisms. Given this need, our task then as computational scientists is to design data structures for representing partial causal knowledge, and algorithms for updating that knowledge in …

Effective And Efficient Transfer Learning In The Era Of Large Language Models, Tu Vu

Doctoral Dissertations

Substantial progress has been made in the field of natural language processing (NLP) due to the advent of large language models (LLMs)—deep neural networks with millions or billions of parameters pre-trained on large amounts of unlabeled data. However, these models have common weaknesses, including degenerate performance in data-scarce scenarios, and substantial computational resource requirements. This thesis aims to develop methods to address these limitations for improved applicability and performance of LLMs in resource-constrained settings with limited data and/or computational resources.

To address the need for labeled data in data-scarce scenarios, I present two methods, in Chapter 2 and Chapter 3, …

Towards Understanding The Geospatial Skills Of Chatgpt: Taking A Geographic Information Systems (Gis) Exam, Peter Mooney, Wencong Cui, Boyuan Guan, Levente Juhasz

GIS Center

This paper examines the performance of ChatGPT, a large language model (LLM), in a geographic information systems (GIS) exam. As LLMs like ChatGPT become increasingly prevalent in various domains, including education, it is important to understand their capabilities and limitations in specialized subject areas such as GIS. Human learning of spatial concepts significantly differs from LLM training methodologies. Therefore, this study aims to assess ChatGPT's performance and ability to grasp geospatial concepts by challenging it with a real GIS exam. By analyzing ChatGPT's responses and evaluating its understanding of GIS principles, we gain insights into the potential applications and challenges …

Uavs And Deep Neural Networks: An Alternative Approach To Monitoring Waterfowl At The Site Level, Zachary J. Loken

LSU Master's Theses

Understanding how waterfowl respond to habitat restoration and management activities is crucial for evaluating and refining conservation delivery programs. However, site-specific waterfowl monitoring is challenging, especially in heavily forested systems such as the Mississippi Alluvial Valley (MAV)—a primary wintering region for ducks in North America. I hypothesized that using uncrewed aerial vehicles (UAVs) coupled with deep learning-based methods for object detection would provide an efficient and effective means for surveying non-breeding waterfowl on difficult-to-access restored wetland sites. Accordingly, during the winters of 2021 and 2022, I surveyed wetland restoration easements in the MAV using a UAV equipped with a dual …

Physics-Informed Neural Networks For Agent-Based Epidemiological Model Calibration, Alvan C. Arulandu, Padmanabhan Seshaiyer

Annual Symposium on Biomathematics and Ecology Education and Research

No abstract provided.

Disease Informed Neural Network And Mathematical Modeling Of Covid-19 With Human Intervention, Jeremis Morales-Morales, Alonso Gabriel Ogueda, Carmen Caiseda, Padmanabhan Seshaiyer

Annual Symposium on Biomathematics and Ecology Education and Research

No abstract provided.

Smartphone Based Object Detection For Shark Spotting, Darrick W. Oliver

Master's Theses

Given concern over shark attacks in coastal regions, the recent use of unmanned aerial vehicles (UAVs), or drones, has increased to ensure the safety of beachgoers. However, much of city officials' process remains manual, with drone operation and review of footage still playing a significant role. In pursuit of a more automated solution, researchers have turned to the usage of neural networks to perform detection of sharks and other marine life. For on-device solutions, this has historically required assembling individual hardware components to form an embedded system to utilize the machine learning model. This means that the camera, neural processing …