Open Access. Powered by Scholars. Published by Universities.®

Physical Sciences and Mathematics Commons™

Open Access. Powered by Scholars. Published by Universities.®

Computer Sciences

University of Louisville

2020

Articles 1 - 6 of 6

Full-Text Articles in Physical Sciences and Mathematics

Exploring Information For Quantum Machine Learning Models, Michael Telahun Dec 2020

Exploring Information For Quantum Machine Learning Models, Michael Telahun

Electronic Theses and Dissertations

Quantum computing performs calculations by using physical phenomena and quantum mechanics principles to solve problems. This form of computation theoretically has been shown to provide speed ups to some problems of modern-day processing. With much anticipation the utilization of quantum phenomena in the field of Machine Learning has become apparent. The work here develops models from two software frameworks: TensorFlow Quantum (TFQ) and PennyLane for machine learning purposes. Both developed models utilize an information encoding technique amplitude encoding for preparation of states in a quantum learning model. This thesis explores both the capacity for amplitude encoding to provide enriched state …

Go to article

Chess As A Testing Grounds For The Oracle Approach To Ai Safety, James D. Miller, Roman Yampolskiy, Olle Häggström, Stuart Armstrong Sep 2020

Chess As A Testing Grounds For The Oracle Approach To Ai Safety, James D. Miller, Roman Yampolskiy, Olle Häggström, Stuart Armstrong

Faculty Scholarship

To reduce the danger of powerful super-intelligent AIs, we might make the first such AIs oracles that can only send and receive messages. This paper proposes a possibly practical means of using machine learning to create two classes of narrow AI oracles that would provide chess advice: those aligned with the player's interest, and those that want the player to lose and give deceptively bad advice. The player would be uncertain which type of oracle it was interacting with. As the oracles would be vastly more intelligent than the player in the domain of chess, experience with these oracles might …

Go to article

A Gis-Based Method For Archival And Visualization Of Microstructural Data From Drill Core Samples., Elliott Holmes Aug 2020

A Gis-Based Method For Archival And Visualization Of Microstructural Data From Drill Core Samples., Elliott Holmes

Electronic Theses and Dissertations

Core samples obtained from scientific drilling could provide large volumes of direct microstructural and compositional data, but generating results via the traditional treatment of such data is often time-consuming and inefficient. Unifying microstructural data within a spatially referenced Geographic Information System (GIS) environment provides an opportunity to readily locate, visualize, correlate, and explore the available microstructural data. Using 26 core billet samples from the San Andreas Fault Observatory at Depth (SAFOD), this study developed procedures for: 1. A GIS-based approach for spatially referenced visualization and storage of microstructural data from drill core billet samples; and 2. Producing 3D models of …

Go to article

Novel Inference Methods For Generalized Linear Models Using Shrinkage Priors And Data Augmentation., Arinjita Bhattacharyya May 2020

Novel Inference Methods For Generalized Linear Models Using Shrinkage Priors And Data Augmentation., Arinjita Bhattacharyya

Electronic Theses and Dissertations

Generalized linear models have broad applications in biostatistics and sociology. In a regression setup, the main target is to find a relevant set of predictors out of a large collection of covariates. Sparsity is the assumption that only a few of these covariates in a regression setup have a meaningful correlation with an outcome variate of interest. Sparsity is incorporated by regularizing the irrelevant slopes towards zero without changing the relevant predictors and keeping the resulting inferences intact. Frequentist variable selection and sparsity are addressed by popular techniques like Lasso, Elastic Net. Bayesian penalized regression can tackle the curse of …

Go to article

Modeling And Counteracting Exposure Bias In Recommender Systems, Sami Khenissi, Olfa Nasraoui Jan 2020

Modeling And Counteracting Exposure Bias In Recommender Systems, Sami Khenissi, Olfa Nasraoui

Faculty Scholarship

What we discover and see online, and consequently our opinions and decisions, are becoming increasingly affected by automated machine learned predictions. Similarly, the predictive accuracy of learning machines heavily depends on the feedback data that we provide them. This mutual influence can lead to closed-loop interactions that may cause unknown biases which can be exacerbated after several iterations of machine learning predictions and user feedback. Machine-caused biases risk leading to undesirable social effects ranging from polarization to unfairness and filter bubbles. In this paper, we study the bias inherent in widely used recommendation strategies such as matrix factorization. Then we …

Go to article

Automatic Target Recognition With Deep Metric Learning., Abdelhamid Bouzid Jan 2020

Automatic Target Recognition With Deep Metric Learning., Abdelhamid Bouzid

Electronic Theses and Dissertations

An Automatic Target Recognizer (ATR) is a real or near-real time understanding system where its input (images, signals) are obtained from sensors and its output is the detected and recognized target. ATR is an important task in many civilian and military computer vision applications. The used sensors, such as infrared (IR) imagery, enlarge our knowledge of the surrounding environment, especially at night as they provide continuous surveillance. However, ATR based on IR faces major challenges such as meteorological conditions, scale and viewpoint invariance. In this thesis, we propose solutions that are based on Deep Metric Learning (DML). DML is a …

Go to article