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 17 of 17 for “"Dynamics Learning"”.
-
Probability and Representation in Neural Systems: Dynamics, Learning, and Computation
… sampling capacity to the score functions their dynamics can approximate and shows that reservoir-sampler architectures can approximate a broad class of target score fields on compact regions. We also examine pretrained video-language models' task-completion token probabilities and use them as …
-
Essays on macroeconomic dynamics: learning, uncertainty, and heterogeneity in credit crises
… 4 are an investigation into the distribution and dynamics of household debt. We present new empirical facts on the distributional dynamics of household debt around the Great Recession in the US using survey data from the Panel Study of Income Dynamics. We document that it is the 60% of households …
-
Choosing To Thrive: Finding Self And Fulfillment Through My Organizational Dynamics Learning Journey
… life. Various frameworks from the Organizational Dynamics program and other influential experiences have given me the tools to reposition my thinking more purposefully, and to create a vision for living and to uncover my potential as an instrument of change. I describe the powerful moments that …
-
Reinforcement Learning Control with Approximation of Time-Dependent Agent Dynamics
Reinforcement Learning has received a lot of attention over the years for systems ranging from static game playing to dynamic system control. Using Reinforcement Learning for control of dynamical systems provides the benefit of learning a control policy without needing a model of the dynamics. This …
-
Examining the Mediating Effect of Employee Engagement in the Relationships between Organizational Learning, Perceived Organizational Support and Employee Performance Outcomes in Vietnamese Small and Medium Enterprises
… in the relationships between organizational learning, perceived organizational support and employee performance outcomes in Vietnamese small and medium enterprises (SMEs). Using a cross-sectional survey design on a sample of 425 employees, four salient findings have been reported from the …
-
Neural Networks as Add-on Modules for Improved Performance of Robot Control Systems
… these control techniques often rely on a dynamics model of the robot, and any inaccuracies in the model can result in suboptimal performance or even unsafe actions. These limitations motivate the incorporation of machine learning into the traditional robot decision-making stack to identify …
-
Data-Driven and Physics-Aware Machine Learning Methods for Mechanical System Analysis
… an input-output model that describes the system dynamics. Learning the FRF of a mechanical system can facilitate system identification, adaptive control, and condition-based health monitoring. In this thesis, learning FRFs from operational data with a nonlinear regression approach is …
-
On the Adaptation of Latent Dynamics Models
… difficulty of accessing the system’s underlying dynamics directly. Classical optimization and analytical approaches become impractical as the dimensionality increases, leading to a growing interest in data-driven deep learning models, particularly those based on latent dynamics functions. Latent …
-
Exploiting Low-Dimensional Structures in Neural Network Approximation: Generative Modeling and Latent Dynamics
… modern science and engineering. Machine learning methods involving neural networks have been widely utilized in applications such as generating realistic videos, surrogate modeling of physical systems, and next token prediction for text. In these cases, the datasets themselves are large …
-
A Learning Approach for Extending Human-Robot Collaboration to Manufacturing-Specific Tasks
… main contribution of this thesis is an imitation learning method that produces dynamical models of a manufacturing task in order to address these limitations. The method (i) learns a structured model of the data, including positions, velocities, accelerations, and forces; (ii) performs a …
-
TranDynaMo: A comparative study of transformer and GRU performance in modeling dynamical systems
Submission published under a 24 month embargo labeled 'Closed Access', the embargo will last until 2025-12-01
-
Information Measures and Deep Learning Techniques for Network Inference
… caveats. (4) We introduce Dynode, a deep-learning-based software package to broaden the scope of understanding the governing dynamics of cell development processes. The goal is not just to identify causal relationships but also to predict the future state of individual cells based on their …
-
Effects of Computer Simulation and Animation (CSA) on Students’ Problem Solving in Engineering Dynamics: What and How
… simulation and animation (CSA) improve students’ learning and problem solving. However, despite the massive body of research on the role of computers in education, little research has been conducted to qualitatively examine how they affect the learning of engineering students. The purpose of this …
-
Transforming Ourselves and Transforming Our Community: A Case Study of Learning Theory and Practice within Society of the Universal Learner in Bihar, India
… and focus group discussions to examine the dynamics of learning within Society of the Universal Learner (SOUL), a community-based organization operating in Bihar, India. The study found that SOUL was already using a wide range of tools, strategies, and approaches to learn about complex …
-
Peer Education: Building Community Through Playback Theatre Action Methods
… community. The impact of action methods on group dynamics and the relationship among methods, individual perceptions, and the acquisition of knowledge were analyzed. The researcher suggested that playback theatre action methods provided a climate in which groups can improve the quality of their …
-
Essays on Market Dynamics in the Presence of Learning
I investigate how the presence of learning affects the market dynamics in three different market settings. The first chapter studies how the interplay of individual and social learning affects price dynamics. I consider a monopolist selling a new experience good over time to many buyers. Buyers …
-
Characterizing Quantum States and Dynamics
Learning states and noise is a crucial part of quantum computation, whether it is to verify state preparation, benchmark gates, or learn the final outcome of a quantum circuit. The complexity of learning can also reveal the complexity of the entity at hand, lending the task information theoretic …