Global ETD Search
Search theses and dissertations gathered from participating repositories worldwide. Every result links back to the library that holds it. No account is needed.
Results
Showing 1 to 20 of 43 for “"Machine learning theory"”.
-
Transparent Machine Learning: Theory and Computation
Modern machine learning is driven primarily by black-box models, which provide superior performance but offer limited transparency into how predictions are made. For applications where it is important to understand how models make decisions, and to assist in model debugging and data-driven …
-
PHYSICS-INFORMED MACHINE LEARNING: THEORY, ALGORITHMS AND APPLICATIONS
The remarkable potential of deep learning in areas from computer vision to natural language processing has now found profound implications in modeling and simulating physical systems. Central to these advancements is the emerging field of physics-informed machine learning, a fusion of physical …
-
Stochastic Gradient Descent For Modern Machine Learning: Theory, Algorithms And Applications
Tremendous advances in large scale machine learning and deep learning have been powered by the seemingly simple and lightweight stochastic gradient method. Variants of the stochastic gradient method (based on iterate averaging) are known to be asymptotically optimal (in terms of predictive …
-
Statistical machine learning theory and methods for high-dimensional low sample size (HDLSS) problems
… have been popular nowadays in statistical machine learning fields. Such applications involves a huge number of features or variables, but sample size is limited due to reasons such as cost, ethnicity and etc. It is important to find approaches to learn the underlying relationships via a …
-
Approximating Bayes: Inference and Modeling
… sources of error in modern Bayesian analysis and machine learning in the ``big data'' era. We develop new theoretical tools for analyzing and controlling different sources of error. Our work leads to new theory and methodology for providing performance guarantees for modern Bayesian methods and …
-
Numerical methods for chemical analysis of complex surfaces
… approach for TPD analysis based on Bayesian machine learning theory is introduced to quantify uncertainty in extracted kinetic parameters. This approach is also modified for application to Gaussian mixture decomposition. These methods are applied to surface analysis of metal-organic …
-
Learning with non-Standard Supervision
Machine learning has enjoyed astounding practical success in a wide range of applications in recent years-practical success that often hurries ahead of our theoretical understanding. The standard framework for machine learning theory assumes full supervision, that is, training data consists of …
-
The Impact Of Artificial Intelligence And Neuro-Linguistic Programming On Candidate Assessment In Talent Acquisition
… study is grounded in Technological Determinism, Machine Learning Theory, Psycholinguistic Theory, and Cognitive Behaviorism. A quantitative correlational approach was used in this study. To investigate the proposed research questions, descriptive statistics, Pearson correlations, simple …
-
Efficient Neural Architecture Search for Automated Deep Learning
Deep learning has been widely applied for its success in many real-world applications. To adopt deep learning, people often need to go through a non-trivial learning curve like learning the foundation of machine learning theory and how to use the deep learning libraries. Automated deep learning has …
-
Can a Neural ODE learn a Chaotic System?
Learning chaotic dynamical systems from data presents significant challenges due to their inherent unpredictability and high sensitivity to initial conditions. Conventional metrics of model performance, such as generalization error, often fail to capture a neural network's ability to reproduce the …
-
Machine learning-based design of doppler tolerant radar
<p>In this work, machine learning theory is applied to the design of a radar detector in order to train a machine learning-based detector that is robust against Doppler shifts. The radar system is designed to work with data that would be otherwise intractable to conventional optimal detector …
-
Brain Signal Quantification and Functional Unit Analysis in Fluorescent Imaging Data by Unsupervised Learning
… an innovative analysis platform built upon machine learning theory. AQuA2 features a novel event detection pipeline for precise quantification of intricate brain signals and incorporates a Consensus Functional Unit (CFU) module to explore interactions among potential functional units driving …
-
New computational and statistical characterizations of neural network learning
A foundational goal of machine learning theory is to characterize the inherent computational and statistical complexity of some of the most basic tasks in machine learning. In this thesis, we present new results concerning two such tasks in neural network learning and beyond. First, we study the …
-
Multivariate Bayesian Machine Learning Regression for Operation and Management of Multiple Reservoir, Irrigation Canal, and River Systems
… of this dissertation is to develop Bayesian machine learning models for multiple reservoir, irrigation canal, and river system operation and management. These types of models are derived from the emerging area of machine learning theory; they are characterized by their ability to capture the …
-
Demonstration of Visible and Near Infrared Raman Spectrometers and Improved Matched Filter Model for Analysis of Combined Raman Signals
… Due to limits in the architectures of current machine learning based Raman classification models, transfer from pure to mixed sample analysis is not possible. This thesis presents the design, fabrication, and data collected from two different Raman spectrometers, a visible light system …
-
Methods and Applications for Probing Deep Neural Networks
… the validity, I apply tools from information theory to derive the error terms of several probing configurations. The reliability problem concerns whether the interpretation test results can be reproduced if this test were conducted again. I use tools in machine learning theory to derive a …
-
Halfway to Halfspace Testing
… appear in many places, including social choice theory (the theory of voting rules), circuit complexity theory, machine learning theory, hardness of approximation, and the analysis of boolean functions. The problem of testing halfspaces, in the sense of property testing, is to design an algorithm …
-
Theories and Methodologies for Cognitive Machine Learning based on Denotational Mathematics
Learning is a cognitive process of knowledge and behavior acquisition for both humans and machines. Cognitive machine learning systems are increasingly demanded in modern knowledge-based industry, society, and everyday lives. This study on theories and applications of cognitive machine learning …
-
New Methodology for Measuring Semantic Functional Similarity Based on Bidirectional Integration
… matrices derived from principles of multi-view learning in machine learning algorithm and five different databases including Gene Ontology, UniProt, SCOP, CATH, and KUPS. The proposed method also shows how diverse databases and principles in machine learning theory can be integrated into a …
Page 1 of 3