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 1931 for “"Limited data"”.
-
DEEP LEARNING UNDER LIMITED DATA ACCESS
Deep learning often faces challenges due to limited access to training data. This thesis addresses these constraints through three key paradigms: continual learning, federated learning, and generative data augmentation. Continual Learning suffers from catastrophic forgetting as models learn …
-
Learning with Limited Data and Supervision
… the great success, these models are known as data-hungry models requiring many labelled training examples and costly computational resources to solve a pre-determined task. Several obstacles limit the applicability of deep learning models in real-world scenarios. First, annotating large-scale …
-
Continual foreground segmentation using limited data
… great success when trained with massive labeled datasets. However, these models have limitations including 1) they can not capture the fine details of the exterior silhouette of objects. 2) The performance of these models degrades when trained with limited data. 3) The performance of these models …
-
Automatic speech segmentation with limited data
… techniques were characterised under different data conditions and the efficient application of these techniques were investigated in order to improve the accuracy of resulting phonetic alignments. We found that the application of baseline speaker-specific Hidden Markov Models results in …
-
Modelling permafrost hydrology using limited data
… soil moisture, snowmelt and evaporation. Input data include only precipitation, global solar radiation, and air temperature. This model has not been calibrated for the High Arctic and only limited field testing has been performed. This study used field measurements from Resolute, Northwest …
-
MACHINE LEARNING FOR LIMITED DATA VOICE CONVERSION
… for voice conversion under the constraint of limited training data. Firstly, a new voice conversion approach is proposed to address the problem of limited training data with and without parallel data, where phonetic information is introduced to the exemplar-based voice conversion framework. …
-
Learning Differential Equations from Noisy, Limited Data
… mechanistic extrapolations for experimental data collected from a natural system. At its core, this approach relies on pattern recognition, a task that machine learning excels at. However, conventional ML models often must be trained using large, “clean” data sets. Scientific data, by …
-
Learning visual recognition models with limited data
… semantic segmentation. Training with extensive datasets is key to enhancing model generalization, enabling accurate predictions on new data and adaptability to real-world complexities. However, despite the exceptional benefits, challenges arise due to the cost associated with data acquisition …
-
Learning Deep Features for Limited-data Visual Problems
… especially when faced with the challenge of limited data, leveraging innovative mechanisms for learning deep features becomes critical. This thesis presents five works to tackle limited-data visual problems, including low-shot and open-set scenarios. In the first work, few-shot recognition is …
-
Learning to Build Probabilistic Models with Limited Data
… features from scratch on large amounts of data. Yet there are many real-world scenarios in which a new model must be built quickly with only a small amount of data. This naturally raises the question: How can we use deep learning to efficiently build task-specific models given limited data? …
-
FACIAL EXPRESSION RECOGNITION AND EDITING WITH LIMITED DATA
… methods usually need large amounts of annotated data. In practice, not all computer vision tasks have access to large amounts of annotated data. Facial expression analysis is such a task. In this dissertation, we focus on facial expression recognition and editing problems with small datasets. In …
-
Attention-based Time Series Forecasting with Limited Data
… production downtime and capital losses. However, data collected in power systems are usually limited and unbalanced because of the very few historical predictable faults. This study focused on evaluating more recently popular attention-based machine learning models for time series prediction in …
-
Bayesian Methods for Graphical Models with Limited Data
… This can be challenging in settings where data is limited and noisy. Take survey data as an example, understanding the associations between questions may help researchers better explain themes amongst related questions and impute missing values. Yet, such data typically contains a …
-
Spatial priors for tomographic reconstructions from limited data
Tomografie is het reconstrueren van het inwendige van een object a.d.h.v externe metingen, b.v. beelden verkregen met X-stralen of microgolven. Deze thesis bekijkt de specifieke aspecten van microgolftomografie en magnetische resonantie beeldvorming (Magnetic Resonance Imaging – MRI); beide …
-
LABEL-EFFICIENT LEARNING: BUILDING AI MODELS WITH LIMITED DATA
Modern deep learning relies on large-scale datasets with high-quality labels, which are expensive and time-consuming to acquire. In many real-world scenarios only limited labeled data is available, which is insufficient for training well-generalized models. This thesis advances label-efficient …
-
Modelling freshwater ecological systems under limited data and knowledge
… being physical, chemical and biological. Data is often lacking to describe the processes within the system and their interactions. This thesis explores how modelling can be used to help understand and manage such complex systems under limited data and knowledge, by examining two Australian …
-
Uncertainty-Aware Meta-Learning for Learning from Limited Data
… (DL) models have achieved great success in large data fields ranging from computer vision and natural language processing to digital arts and robotics. However, the effectiveness of the DL models is challenged by many real-world limited data problems (e.g., medicine, healthcare, and security …
-
Probabilistic uncertainty quantification for structural dynamics under limited data
<p>Two grand challenges under the context of limited data availability in structural dynamics are faced in this thesis: the design of complex engineering structures, and the updating of data on already existing critical structures by integration of physics-based models. The motivation to confront …
Page 1 of 97