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 58 for “"Data-Efficiency"”.
-
Data augmentation and data efficiency for low-resource language processing
Submission published under a 24 month embargo labeled 'U of I Access', the embargo will last until 2027-05-01
-
Towards Data Efficiency and Controllable Representations for Deep Learning in Resource-Constrained Domains
… two fundamental challenges: label scarcity and data scarcity. Label scarcity stems from the high cost of expert annotation, the scarcity of domain experts, and the infeasibility of crowdsourcing, particularly in complex tasks requiring specialised knowledge. In parallel, data scarcity stems from …
-
Bridging Deep Learning and Probabilistic Inference: Towards Data Efficiency, Identifiability, and Sampling Scalability
… in modelling complex patterns in structured data, a key challenge is its reliance on large datasets. In contrast, probabilistic inference excels in data-scarce settings but suffers from computational inefficiencies for high dimensional data and struggles to model structured data where …
-
Detection of the uniqueness of a human voice: towards machine learning for improved data efficiency
The aim of this thesis is to characterise voice characteristics that can establish the identity of the person who is speaking, independent of the language used. The fundamental goal of the work is to understand how humans recognise a speaker. The voice parameters such as: speech rate, natural …
-
Structural Priors for Active Learning on Robots
… to neural networks in robotic applications is data efficiency; collecting data on a real robot is slow and expensive. Active learning, in which the learner chooses the data that will best accelerate learning, has been shown to reduce data requirements in machine learning and statistics …
-
ENHANCING DEEP LEARNING WITH SYMBOLIC DOMAIN KNOWLEDGE
… flexibility, deep models have two drawbacks: low data efficiency and a lack of robustness. Firstly, deep neural networks often require large amounts of training data. On the other hand, symbolic domain knowledge is often available in addition to data. The first part of this thesis aims to improve …
-
Bayesian Learning for Data-Efficient Control
… system interaction. This thesis considers data efficient autonomous learning of control of nonlinear, stochastic systems. Data efficient learning critically requires probabilistic modelling of dynamics. Traditional control approaches use deterministic models, which easily overfit data, …
-
Improving Deep Learning with Probabilistic Approaches
… it struggles with uncertainty quantification and data efficiency. Probabilistic methods, while currently somewhat underappreciated by the wider machine learning community, provide calibrated uncertainty estimates and tend to shine in the low-data regime. It would seem that probabilistic methods …
-
Achieving More with Less: Learning Generalizable Neural Networks With Less Labeled Data and Computational Overheads
… patterns and relationships automatically from data in a number of mainstream applications. However, the generalization power of deep learning methods largely comes at the costs of working with very large datasets and using highly compute-intensive models. Many applications cannot afford these …
-
EFFICIENT DATA CURATION AND UTILIZATION FOR DEEP LEARNING
… methods to improve the training and construction efficiency of large-scale vision datasets, aiming to reduce computational and annotation costs. We propose InfoBatch, an unbiased dynamic data pruning framework that losslessly accelerates training and saves 20–40% of computation across diverse …
-
Enhancing surrogate models of engineering structures with graph-based and physics-informed learning
… surrogate models are often limited by data availability, since designs and performance data can be expensive to produce. This work shows that transfer learning, through which training data of varying topology, complexity, loads and applications are repurposed for new predictive tasks, …
-
Scalable Mining and Link Analysis Across Multiple Database Relations
Because of the complexity of multi-relational data, efficiency and scalability are two major concerns in multi-relational data mining. In this thesis we propose scalable and accurate approaches for each data mining task studied. In order to achieve high efficiency and scalability, the approaches …
-
Data Efficient Reinforcement Learning
… However, many state-of-the-art algorithms are data-hungry and computationally expensive, requiring large amounts of data to succeed. While this is possible for certain scenarios, in applications arising in social sciences and healthcare for example, where available data is sparse, this …
-
On the Resource Efficiency of Language Models
… faces resource challenges in two dimensions: data efficiency and model efficiency. For post-training, LLMs face data curation challenges where high-quality labeled data is scarce and expensive to obtain, and data utilization challenges where existing methods fail to optimize model performance …
-
Advancing Efficiency and Safety in Autonomous Sequential Decision Making
… obstacles, chiefly in achieving sample (data) efficiency and ensuring agent safety in unpredictable, dynamic environments. Additionally, the inherent partial knowledge due to sensory and model limitations complicates agents' functionality in complex scenarios. This thesis aims to enhance …
-
Radio propagation analysis for improved UAV data muling of surfaced underwater sensor nodes
… waypoint selection and evaluation mechanisms for data muling water sensor nodes via unmanned air vehicle. We present a mathematical model for predicting signal strength with respect to distance and height using a two-ray propagation model in conjunction with the individual radiation patterns of …
-
TOWARDS DATA-EFFICIENT DEEP LEARNING
This thesis advances data-efficient machine learning by tackling the limitations of current dataset distillation (DD) methods, which aim to compress large datasets into compact synthetic ones for faster training and enhanced privacy. First, it introduces Dataset Factorization, a novel framework …
-
Data-Efficient Machine Learning for Computational Imaging
This thesis presents a method that improves data efficiency in computational imaging by incorporating prior knowledge from physical models into machine learning algorithms. Our approach optimizes image reconstruction from sparse and noisy datasets by utilizing physical constraints to guide deep …
-
University course registration and management system : a distributed application using Microsoft distributed component object model
… (presentation-tier, application-tier, and data-tier), distributed application capable of running on number of PCs according to the configuration. It provides a convenient graphic user interface for both students and university administrators. It allows students to make a self-registration …
-
Model-based approaches for learning control from multi-modal data
… to real-world systems due to poor sample efficiency and inability to handle state and control constraints. We introduce and demonstrate a general paradigm that combines model-learning and online planning for control which can also handle a wide range of problems using traditional and …
Page 1 of 3