Artificial Intelligence and Robotics Commons^™

Algorithmic Bias: Causes And Effects On Marginalized Communities, Katrina M. Baha

Undergraduate Honors Theses

Individuals from marginalized backgrounds face different healthcare outcomes due to algorithmic bias in the technological healthcare industry. Algorithmic biases, which are the biases that arise from the set of steps used to solve or analyze a problem, are evident when people from marginalized communities use healthcare technology. For example, many pulse oximeters, which are the medical devices used to measure oxygen saturation in the blood, are not able to accurately read people who have darker skin tones. Thus, people with darker skin tones are not able to receive proper health care due to their pulse oximetry data being inaccurate. This …

Detecting Ai Generated Text Using Neural Networks, Jesus Guerrero

Masters Theses (Archived)

For humans, distinguishing machine generated text from human written text is men- tally taxing and slow. NLP models have been created to do this more effectively and faster. But, what if some adversarial changes have been added to the machine generated text? This thesis discusses this issue and text detectors in general.
/="/">
/="/">The primary goal of this thesis is to describe the current state of text detectors in research and to discuss a key adversarial issue in modern NLP transformers. To describe the current state of text detectors a Systematic Literature Review was done on 50 relevant papers …

Using Deep Neural Networks To Classify Astronomical Images, Andrew D. Macpherson

Honors Projects

As the quantity of astronomical data available continues to exceed the resources available for analysis, recent advances in artificial intelligence encourage the development of automated classification tools. This paper lays out a framework for constructing a deep neural network capable of classifying individual astronomical images by describing techniques to extract and label these objects from large images.

Several Thoughts On Information Technology Driving Future Industries, Yungang Bao, Miao Liu, Pinyan Lu, Xipeng Qiu, Jiang Xu

Bulletin of Chinese Academy of Sciences (Chinese Version)

No abstract provided.

The Model 2.0 And Friends: An Interim Report, Garrison W. Cottrell, Martha Gahl, Shubham Kulkarni, Shashank Venkatramani, Yash Shah, Keyu Long, Xuzhe Zhi, Shivaank Agarwal, Cody Li, Jingyuan He, Thomas Fischer

MODVIS Workshop

Last year, I reported on preliminary results of an anatomically-inspired deep learning model of the visual system and its role in explaining the face inversion effect. This year, I will report on new results and some variations on network architectures that we have explored, mainly as a way to generate discussion and get feedback. This is by no means a polished, final presentation!

We look forward to the group’s suggestions for these projects.

Automated Delineation Of Visual Area Boundaries And Eccentricities By A Cnn Using Functional, Anatomical, And Diffusion-Weighted Mri Data, Noah C. Benson, Bogeng Song, Toshikazu Miyata, Hiromasa Takemura, Jonathan Winawer

MODVIS Workshop

Delineating visual field maps and iso-eccentricities from fMRI data is an important but time-consuming task for many neuroimaging studies on the human visual cortex because the traditional methods of doing so using retinotopic mapping experiments require substantial expertise as well as scanner, computer, and human time. Automated methods based on gray-matter anatomy or a combination of anatomy and functional mapping can reduce these requirements but are less accurate than experts. Convolutional Neural Networks (CNNs) are powerful tools for automated medical image segmentation. We hypothesize that CNNs can define visual area boundaries with high accuracy. We trained U-Net CNNs with ResNet18 …

How Object Segmentation And Perceptual Grouping Emerge In Noisy Variational Autoencoders, Ben Lonnqvist, Zhengqing Wu, Michael H. Herzog

MODVIS Workshop

Many animals and humans can recognize and segment objects from their backgrounds. Whether object segmentation is necessary for object recognition has long been a topic of debate. Deep neural networks (DNNs) excel at object recognition, but not at segmentation tasks - this has led to the belief that object recognition and segmentation are separate mechanisms in visual processing. Here, however, we show evidence that in variational autoencoders (VAEs), segmentation and faithful representation of data can be interlinked. VAEs are encoder-decoder models that learn to represent independent generative factors of the data as a distribution in a very small bottleneck layer; …

A Dynamical Model Of Binding In Visual Cortex During Incremental Grouping And Search, Daniel Schmid, Daniel A. Braun, Heiko Neumann

MODVIS Workshop

Binding of visual information is crucial for several perceptual tasks. To incrementally group an object, elements in a space-feature neighborhood need to be bound together starting from an attended location (Roelfsema, TICS, 2005). To perform visual search, candidate locations and cued features must be evaluated conjunctively to retrieve a target (Treisman&Gormican, Psychol Rev, 1988). Despite different requirements on binding, both tasks are solved by the same neural substrate. In a model of perceptual decision-making, we give a mechanistic explanation for how this can be achieved. The architecture consists of a visual cortex module and a higher-order thalamic module. While the …

Artificial Intelligence In Neuroradiology: A Scoping Review Of Some Ethical Challenges, Pegah Khosravi, Mark Schweitzer

Publications and Research

Artificial intelligence (AI) has great potential to increase accuracy and efficiency in many aspects of neuroradiology. It provides substantial opportunities for insights into brain pathophysiology, developing models to determine treatment decisions, and improving current prognostication as well as diagnostic algorithms. Concurrently, the autonomous use of AI models introduces ethical challenges regarding the scope of informed consent, risks associated with data privacy and protection, potential database biases, as well as responsibility and liability that might potentially arise. In this manuscript, we will first provide a brief overview of AI methods used in neuroradiology and segue into key methodological and ethical challenges. …

Ptmtorrent: A Dataset For Mining Open-Source Pre-Trained Model Packages, Wenxin Jiang, Nicholas Synovic, Purvish Jajal, Taylor R. Schorlemmer, Arav Tewari, Bhavesh Pareek, George K. Thiruvathukal, James C. Davis

Computer Science: Faculty Publications and Other Works

Due to the cost of developing and training deep learning models from scratch, machine learning engineers have begun to reuse pre-trained models (PTMs) and fine-tune them for downstream tasks. PTM registries known as “model hubs” support engineers in distributing and reusing deep learning models. PTM packages include pre-trained weights, documentation, model architectures, datasets, and metadata. Mining the information in PTM packages will enable the discovery of engineering phenomena and tools to support software engineers. However, accessing this information is difficult — there are many PTM registries, and both the registries and the individual packages may have rate limiting for accessing …

Feature Selection From Clinical Surveys Using Semantic Textual Similarity, Benjamin Warner

McKelvey School of Engineering Graduate Student Theses & Dissertations

Survey data collected from human subjects can contain a high number of features while having a comparatively low quantity of examples. Machine learning models that attempt to predict outcomes from survey data under these conditions can overfit and result in poor generalizability. One remedy to this issue is feature selection, which attempts to select an optimal subset of features to learn upon. A relatively unexplored source of information in the feature selection process is the usage of textual names of features, which may be semantically indicative of which features are relevant to a target outcome. The relationships between feature names …

An Empirical Study Of Pre-Trained Model Reuse In The Hugging Face Deep Learning Model Registry, Wenxin Jiang, Nicholas Synovic, Matt Hyattt, Taylor R. Schorlemmer, Rohan Sethi, Yung-Hisang Lu, George K. Thiruvathukal, James C. Davis

Computer Science: Faculty Publications and Other Works

Deep Neural Networks (DNNs) are being adopted as components in software systems. Creating and specializing DNNs from scratch has grown increasingly difficult as state-of-the-art architectures grow more complex. Following the path of traditional software engineering, machine learning engineers have begun to reuse large-scale pre-trained models (PTMs) and fine-tune these models for downstream tasks. Prior works have studied reuse practices for traditional software packages to guide software engineers towards better package maintenance and dependency management. We lack a similar foundation of knowledge to guide behaviors in pre-trained model ecosystems.

In this work, we present the first empirical investigation of PTM reuse. …

Optimizing Tumor Xenograft Experiments Using Bayesian Linear And Nonlinear Mixed Modelling And Reinforcement Learning, Mary Lena Bleile

Statistical Science Theses and Dissertations

Tumor xenograft experiments are a popular tool of cancer biology research. In a typical such experiment, one implants a set of animals with an aliquot of the human tumor of interest, applies various treatments of interest, and observes the subsequent response. Efficient analysis of the data from these experiments is therefore of utmost importance. This dissertation proposes three methods for optimizing cancer treatment and data analysis in the tumor xenograft context. The first of these is applicable to tumor xenograft experiments in general, and the second two seek to optimize the combination of radiotherapy with immunotherapy in the tumor xenograft …

Identifying Key Activity Indicators In Rats' Neuronal Data Using Lasso Regularized Logistic Regression, Avery Woods

Honors Theses

This thesis aims to identify timestamps of rats’ neuronal activity that best determine behavior using a machine learning model. Neuronal data is a complex and high-dimensional dataset, and identifying the most informative features is crucial for understanding the underlying neuronal processes. The Lasso regularization technique is employed to select the most relevant features of the data to the model’s prediction. The results of this study provide insights into the key activity indicators that are associated with specific behaviors or cognitive processes in rats, as well as the effect that stress can have on neuronal activity and behavior. Ultimately, it was …

Automatic Identification Of Jetting Behavior In 3d Printing With Binary Classification And Anomaly Detection, Alexander Chandy

Honors Scholar Theses

Consistently jetting different materials from the print head of a 3D printer is a key, yet challenging task in manufacturing processes. By using active machine learning, we can efficiently predict complex diagrams that illustrate the region of printing conditions under which “desirable jetting”, “jetting”, and “no jetting” of ink occurs for different substances. However, labeling the images of printed ink droplets that are fed to the active learning model can be time intensive. Therefore, it is ideal to use computer vision to automate the classification of this image data. This classification can be broken down into two steps. In the …

U-No: U-Shaped Neural Operators, Md Ashiqur Rahman, Zachary E Ross, Kamyar Azizzadenesheli

Department of Computer Science Faculty Publications

Neural operators generalize classical neural networks to maps between infinite-dimensional spaces, e.g., function spaces. Prior works on neural operators proposed a series of novel methods to learn such maps and demonstrated unprecedented success in learning solution operators of partial differential equations. Due to their close proximity to fully connected architectures, these models mainly suffer from high memory usage and are generally limited to shallow deep learning models. In this paper, we propose U-shaped Neural Operator (U-NO), a U-shaped memory enhanced architecture that allows for deeper neural operators. U-NOs exploit the problem structures in function predictions and demonstrate fast training, data …

Pruning Ghsom To Create An Explainable Intrusion Detection System, Thomas Michael Kirby

Theses and Dissertations

Intrusion Detection Systems (IDS) that provide high detection rates but are black boxes lead
to models that make predictions a security analyst cannot understand. Self-Organizing Maps
(SOMs) have been used to predict intrusion to a network, while also explaining predictions through
visualization and identifying significant features. However, they have not been able to compete with
the detection rates of black box models. Growing Hierarchical Self-Organizing Maps (GHSOMs)
have been used to obtain high detection rates on the NSL-KDD and CIC-IDS-2017 network traffic
datasets, but they neglect creating explanations or visualizations, which results in another black
box model.
This paper offers …

Development And Evaluation Of An Automated Tactical Tillage Tool To Control Weeds In Row-Crop Production Systems, Grace Mccormick Friday

Theses and Dissertations

Weed control is an integral part of a successful overall production strategy in row- cropping systems and has the potential to reduce or eliminate yield losses that negatively affect profitability. Timely and correctly selected herbicide applications are the major keys for effective weed control in a majority of instances. However, there are negative factors that contribute to ineffectiveness and weed escape issues that currently lack viable options for management. Sparsely populated late-season weeds that emerge after lay-by herbicide applications and weeds that have become tolerant and resistant to traditional herbicide chemistries are of greatest concern. Historically, these weeds would have …

Secure And Efficient Federated Learning, Xingyu Li

Theses and Dissertations

In the past 10 years, the growth of machine learning technology has been significant, largely due to the availability of large datasets for training. However, gathering a sufficient amount of data on a central server can be challenging. Additionally, with the rise of mobile networking and the large amounts of data generated by IoT devices, privacy and security issues have become a concern, resulting in government regulations such as GDPR, HIPAA, CCPA, and ADPPA. Under these circumstances, traditional centralized machine learning methods face a problem in that sensitive data must be kept locally for privacy reasons, making it difficult to …

Tornado Outbreak False Alarm Probabilistic Forecasts With Machine Learning, Kirsten Reed Snodgrass

Theses and Dissertations

Tornadic outbreaks occur annually, causing fatalities and millions of dollars in damage. By improving forecasts, the public can be better equipped to act prior to an event. False alarms (FAs) can hinder the public’s ability (or willingness) to act. As such, a probabilistic FA forecasting scheme would be beneficial to improving public response to outbreaks.

Here, a machine learning approach is employed to predict FA likelihood from Storm Prediction Center (SPC) tornado outbreak forecasts. A database of hit and FA outbreak forecasts spanning 2010 – 2020 was developed using historical SPC convective outlooks and the SPC Storm Reports database. Weather …