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 385 for “"Unlabeled data"”.
-
Towards Uncovering the True Use of Unlabeled Data in Machine Learning
Knowing how to exploit unlabeled data is a fundamental problem in machine learning. This dissertation provides contributions in different contexts, including semi-supervised learning, positive unlabeled learning and representation learning. In particular, we ask (i) whether is possible to learn a …
-
From Labeled to Unlabeled Data: Understand Deep Visual Representations under Causal Lens
… and object detection. These models encode visual data into low-dimensional representations, which are then utilized in downstream tasks. Typically, the most accurate models are fine-tuned using fully labeled data, but this approach may not generalize well to different applications. Self-supervised …
-
Addressing the data challenge in automatic drum transcription with labeled and unlabeled data
… by the lack of a meaningful amount of labeled data to support the data-driven algorithms. To address this data challenge in ADT, this work presents three approaches. First, a dataset for ADT tasks is created using a semi-automatic process that minimizes the workload of human annotators. Second, …
-
Learning from positive and unlabeled data for imbalanced datasets: theory and real-world applications
Machine Learning (ML) has revolutionized data analysis and decision-making by allow- ing systems to learn and improve from experience, in contrast to traditional program- ming’s rules-based approach. ML algorithms analyze large datasets to uncover patterns and make predictions, improving with more …
-
Semisupervised Learning of Classifiers With Application to Human -Computer Interaction
… by domain experts or by learning from training data. Training data can be labeled to the different classes or unlabeled. In this work I focus on training probabilistic classifiers with labeled and unlabeled data. I show under what conditions unlabeled data can be used to improve classification …
-
Contributions to Unsupervised and Semi-Supervised Learning
… part, we study the relative advantage of having unlabeled data in classification problems. Clustering stability was proposed and used as a model selection method in clustering tasks. The main idea of the method is that from a given data set two independent samples are taken. Each sample …
-
Semi-supervised learning for acoustic and prosodic modeling in speech applications
… prosody detection. However, most of these speech data are not being utilized because they lack transcriptions. The goal of this thesis is to use untranscribed (unlabeled) data to improve the performance of models trained using only transcribed (labeled) data. We propose a unified semi-supervised …
-
Learning without labels and nonnegative tensor factorization
… predictors, are typically performed with labeled data. In most cases, obtaining labeled data is costly as it requires manual labeling. On the other hand, unlabeled data is available in abundance. In this thesis, we discuss methods to perform supervised learning tasks with no labeled data. We prove …
-
Feature Partitioning for the Co-Traning Setting
… algorithms rely on availability of labeled data. Labeled data is either scarce or involves substantial human effort in the labeling process. These two factors, along with the abundance of unlabeled data, have spurred research initiatives that exploit unlabeled data to boost supervised …
-
Explainability in Graph Neural Networks
… with our proposed novel metric on real-world datasets. The second problem is the semi-supervised learning for GNNs. A majority of GNNs studies focus on semi-supervised learning due to the challenge of labeled data shortage in graph-based tasks. To address this challenge, Graph Neural Networks …
-
Landmine detection using semi-supervised learning.
… learning, which requires labeling of known data. This process can be tedious. Semi-supervised learning leverages both labeled and unlabeled data in the training process, alleviating over-dependency on labeling. Semi-supervised learning has several advantages over supervised learning. For …
-
Transfer learning towards combating antibiotic resistance
… as biology where we usually have small labeled data but an abundance of unlabeled data. Using abundant unlabeled data to enhance performance on a small labeled dataset is the hallmark of transfer learning. In this dissertation, I tap into the potential of transfer learning to solve critical …
-
Induction Of Fine-Grained Lexical Parameters Of Treebank Pcfgs With Inside-Outside Estimation And Lexical Transformations
… parameters of a smoothed Penn Treebank PCFG from unlabeled data. The PCFG contains important linguistic representations for argument-adjunct distinctions and long-distance dependencies. The lexical parameters of the PCFG encode fine-grained information about structures selected by a lexical item, …
-
Optimal and Safe Semi-supervised Estimation and Inference for High-dimensional Linear Regression
… to collect than the covariates. We refer data consisting of both covariates and the corresponding outcomes as labeled data, and data with only covariates as unlabeled data. Semi-supervised learning combines both labeled and unlabeled data to improve a model using only labeled data and can …
-
LEARNING UTTERANCE LEVEL REPRESENTATION FROM SPEECH
… about phones, and 2) it cannot leverage data without speaker labels. Phone information remaining in x-vector can degrade its performance in text-independent SV because utterances from the same speaker may have different embeddings due to different phone coverage, or embeddings from two …
Page 1 of 20