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 24 for “"Unlabelled Data"”.
-
Improving Parameter-Efficient Cross-Lingual Transfer for Low-Resource Languages
… low-resource languages, often lacking labelled data while also possessing a limited amount of unlabelled data. The open question is how to best use available data sources to achieve good performance across a range of resource scarcity. In this thesis, this question is addressed from two …
-
Active learning for data streams.
With the exponential growth of data amount and sources, access to large collections of data has become easier and cheaper. However, data is generally unlabelled and labels are often difficult, expensive, and time consuming to obtain. Two learning paradigms have been used by machine learning …
-
Self-supervised learning for data-efficient human activity recognition
… sensing, which involves obtaining and analysing data from mobile devices and the environment, has emerged as an active research area. It captures the unique opportunity for mobile devices to offer insight into user behaviours. Within mobile sensing, human activity recognition is a fundamental …
-
Fuse and Adapt: Investigating the Use of Pre-Trained Self-Supervising Learning Models in Limited Data NLU problems
… DL in most domains is the scarcity of labelled data. Usually, DL models need large amounts of annotated data to train models. The novel paradigm of Self Supervised Learning (SSL) has become a gamechanger in the field of Deep Learning due to its ability to answer the problem of scarcity of …
-
Semi-Supervised Transfer Learning for medical images as an alternative to ImageNet Transfer Learning
… amount of expensive manually labelled training data. Consequently, even in medical imaging, transfer learning from natural image datasets (such as ImageNet) has become the norm. However, this approach has been shown to be ineffective due to the significant differences between medical images and …
-
Classifying tracked objects in far-field video surveillance
… is extracted through passive observation of unlabelled data. Experimental results are demonstrated in the context of outdoor visual surveillance of a wide variety of scenes.
-
Content-based Image Understanding with Applications to Affective Computing and Person Recognition in Natural Settings
… scenarios that has different amount of labelled data. Our algorithm that utilizes unlabelled data reduces the effort needed for data annotation while achieving similar results as with labelled data.
-
Deep Learning-Based Synthesis of Surgical Hyperspectral Images
… parameters during interventions. To capture data emanating from underlying physiological tissue properties, hyperspectral imaging (HSI) together with machine learning-based analyses has been proposed as a solution in recent literature. However, HSI data in the clinical setting is sparse, as …
-
Uncertainty-aware learning from sparse, unlabelled, and out-of-distribution time series
… tracking. The ever-increasing availability of datasets from wearable sensors, mobile devices, and continuous monitoring technologies has created new opportunities for real-world applications, as they can offer a rich and continuous picture of an individual's health and fitness in everyday …
-
Learning meaning representations for text generation with deep generative models
… and whether the variables can be induced from unlabelled data. The latter consideration is particularly interesting: if we can show that induced latent variables correspond to the semantics of the generated utterance, then by manipulating the variables, we have fine-grained control over the …
-
Efficient Bayesian active learning and matrix modelling
… of storage capabilities, large collections of unlabelled data are now available. However, collecting supervised labels can be costly. Active learning addresses this by selecting, sequentially, only the most useful data in light of the information collected so far. The online nature of such …
-
Active learning based on a hybrid neural network modeller
… methods are investigated for selecting training data for the purpose of training neural networks. A new method called MIQR (Maximum Inter-Quartile Range) is proposed for effectively selecting a concise set of training data. In addition, the ensemble concept is introduced in this new method. Data …
-
Modern k-Nearest Neighbour Methods in Entropy Estimation, Independence Testing and Classification
… where, in addition to labelled training data, we also have access to a large sample of unlabelled data.
-
Federated self-supervised learning
… collaborative learning from large-scale datasets without compromising users’ data privacy. However, current FL practices predominantly focus on supervised learning tasks, necessitating the availability of high-quality, domain-specific labels alongside the data. This prerequisite …
-
Minimal Labels, Maximum Gain. Image Classification with Graph-Based Semi-Supervised Learning
… access to a large and representative labelled dataset from which they can optimise their model in a supervised manner. However, in many domains, there is a large cost to obtaining labelled data. In technical fields we need manual annotations from domain experts and for deep learning models we …
-
ScatterNet Hybrid Frameworks for Deep Learning
… of these networks requires large labeled datasets which in numerous applications may not be available. In this dissertation, we propose the ScatterNet Hybrid Framework for Deep Learning that is inspired by the circuitry of the visual cortex. The framework uses a hand-crafted front-end, an …
-
Deep Neural Network for Anomaly Detection
… to deal with new/unknown attacks, imbalanced data, the lack of labelled data, and the vulnerability to data poisoning attacks. First, to detect new/unknown anomalies (attacks) effectively, the thesis proposes a novel representation learning method, i.e., AutoEncoders (AEs) based models, that …
-
Fuzzy Transfer Learning
… use of machine learning to predict output from data, using a model, is a well studied area. There are, however, a number of real-world applications that require a model to be produced but have little or no data available of the specific environment. These situations are prominent in Intelligent …
-
Formulating test oracles via anomaly detection techniques
Developments in the automation of test data generation have greatly improved efficiency of the software testing process but the so-called "oracle problem" (deciding the pass or fail outcome of a test execution) is still primarily an expensive and error-prone manual activity. This thesis presents an …
-
Active and Semi-Supervised Learning for Speech Recognition
… enabled the training of models on ever-expanding data sets, and deep learning allowed for the better exploitation of these large data sets. For commercial products, training on multiple thousands of hours of transcribed audio is common practice. However, the manual transcription of audio comes …
Page 1 of 2