Browsing Faculty of Arts and Sciences by Keyword "Machine Learning"
Now showing items 1-20 of 30
-
A Gaussian-process Framework for Nonlinear Statistical Inference using Modern Machine Learning Models
(2023-05-12)Gaussian Process Regression has become widely used in biomedical research in recent years, particularly for studying the intricate and nonlinear impacts of multivariate genetic or environmental exposures. This dissertation ... -
A Method for Fast Single-Network Uncertainty Estimation in Deep Learning Interatomic Potentials
(2023-06-30)Deep learning has emerged as a promising paradigm for predicting molecular and materials properties with high accuracy. A common shortcoming shared by deep learning neural networks, however, is that they only produce point ... -
Accelerating the Understanding and Design of Intracellular Biosensors by Massively Multiplexed Experimentation and Machine Learning
(2021-01-06)Recent progress in large-scale DNA synthesis and next-generation DNA sequencing technology have enabled studies of biological processes at a massive scale. These studies can be further coupled to advanced computational ... -
Active Learning of Bayesian Force Fields
(2022-01-18)Simulating matter at the atomistic scale can accelerate drug design and materials discovery, but the most accurate atomistic simulation methods are prohibitively expensive. In the past decade, machine learning (ML) has ... -
Activity Allocation in an Under-Resourced World: Toward Improving Engagement with Public Health Programs via Restless Bandits
(2023-08-22)Artificial intelligence (AI) tools are being developed widely within society to improve decision-making, especially in resource-constrained settings like public health. However, developing effective AI tools for public ... -
Analyzing the multidimensionality of aging by using machine learning to predict age from diverse medical datasets
(2021-05-12)The world population is aging, leading to a rise in the prevalence of age-related diseases such as cardiovascular disease and cancer. In parallel to treating the diseases, an attractive idea is to address the problem at ... -
Computation-Cautious Machine Learning Systems
(2021-05-13)Deriving knowledge from data is central to how we live, learn, and decide: Machine learning and data science pipelines are extensively applied to extract knowledge from an ever-increasing amount of data across all fields, ... -
DEADEYE: Differential Expressivity As Dataset fairnEss/usabilitY Estimator
(2022-05-23)Over the past several years, significant research has gone into analyzing algorithmic fairness -- the problem of ensuring ML algorithms do not exhibit biases against protected groups. That research demonstrated that, given ... -
Differentially Private Ridge Regression: The Cost of a Hyperparameter
(2021-06-04)Studying problems of interest, like finding trends in medical data, can require analyzing data which contains sensitive and personally identifying information. As a result, it is often infeasible to release these datasets ... -
Embedded Dense Neural Networks for Battery Cyclability Prediction on Automotive Microcontroller Devices
(2021-06-03)Recent increase in energy demand has resulted in an upsurge of interest in developing efficient battery storage systems and designing scalable machine learning models that predict the performance of these batteries. This ... -
Equity Market Views and Digital Technology Investment in Non-IT Firms
(2022-05-12)Motivated by the increasing investment in digital technologies, such as analytics, big data and artificial intelligence technologies, in non-IT firms, this dissertation studies the role that equity markets play in the ... -
Fully Homomorphic Encryption with Applications to Privacy-Preserving Machine Learning
(2023-06-30)There are two dominant trends today that appear to be mutually exclusive: on the one hand, machine learning services that provide accurate predictions based on personal data have become widespread, but on the other hand, ... -
Information Design in Operations Management
(2021-09-14)Information design – or the practice of effectively communicating information to its audience – is a delicate dance that requires accuracy, clarity, comprehensiveness, and engagement. Yet, even when all these boxes are ... -
Learning Inductive Representations of Biomedical Data
(2020-09-15)Representation learning with neural networks has catalyzed rapid progress in biomedical pattern recognition. This progress, however, has generally been limited to domains where data are abundant, richly structured, and ... -
Materials Informatics for Catalyst Stability & Functionality
(2021-05-13)Accelerating materials design & discovery will be critical to reducing society's dependence on fossil fuel-based energy sources. Computational methods such as density-functional theory, high-throughput workflow automation, ... -
On Neural Linear Model Prediction, with Applications to Nonstationary Settings
(2023-06-30)Neural Linear Models (NLMs) are deep Bayesian machine learning models that appear in a variety of contexts due to their data adaptivity and model flexibility, including many settings where Gaussian Processes (GPs) traditionally ... -
Order by Disorder in Topological Quantum Materials
(2024-03-12)Topological materials are a promising platform for next-generation devices, ranging from optoelectronics to interconnects. In these materials, the interplay between magnetic, electronic, and lattice degrees of freedom ... -
Panacea: Making the World’s Biomedical Information Computable to Develop Data Platforms for Machine Learning
(2022-05-23)The marriage between healthcare and artificial intelligence systems has long been coveted — by computer scientists and medical researchers alike — as a grand challenge to progress the frontier of health. Given the explosion ... -
Revisiting Random Utility Models
(2014-06-06)This thesis explores extensions of Random Utility Models (RUMs), providing more flexible models and adopting a computational perspective. This includes building new models and understanding their properties such as ... -
Scalability and Performance of Intractable Optimization Problems in Machine Learning
(2022-01-18)In this thesis, we study the scalability and performance of combinatorial optimization problems in machine learning. Paradigms such as feature selection, text summarization, and sparse recovery are all examples of machine ...