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 1100 for “"representation learning"”.
-
Sheaf Representation Learning
… which describe these processes, machine learning models must be imbued with structural inductive biases which align the function’s representations with the constraints imposed by the domain topology. Despite this crucial relationship between domain topology and observed data, a general …
-
Signed Graph Representation Learning
… thesis considers the research on signed graph representation learning in different aspects. Signed graphs model complex relations using both positive and negative edges and signed graph neural networks (SGNNs) are powerful tools to analyze signed graphs. Our thesis mainly involves the research …
-
Discriminative Video Representation Learning
Representation learning is a fundamental research problem in the area of machine learning, refining the raw data to discover representations needed for various applications. However, real-world data, particularly video data, is neither mathematically nor computationally convenient to process due to …
-
Representation learning in finance
… from these datasets. This work explores representation learning as a proven machine learning technique in learning informative embedding from complex, noisy, and dynamic financial data. This dissertation proposes novel factorization algorithms and network modeling techniques to learn the …
-
Unsupervised speech representation learning
Representations aim to capture significant, high-level information from raw data, most commonly as low dimensional vectors. When considered as input features for a downstream classification task, they reduce classifier complexity, and help in transfer learning and domain adaptation. An …
-
Global Optimality in Representation Learning
… a wide range of technical disciplines require a representation of the data that is meaningful for the task at hand in order to succeed. In some cases one has enough prior knowledge about the problem that a fixed transformation of the data or set of features can be pre-calculated, but for most …
-
Spatio-temporal Graph Representation Learning
This thesis delves into Spatio-temporal Graph Representation Learning (STGRL), an emerging and specialized subset of Spatio-temporal Data Mining (STDM). STGRL capitalizes on deep learning methodologies applied to the inherent graph structure of spatio-temporal data, thereby facilitating a deeper …
-
Parameter efficient code representation learning
This dissertation addresses efficient code representation learning, embedding code and related text into vectors that capture semantics, syntax, and context to support tasks like code summarization and code generation. We propose four contributions: (1) knowledge transformation via lightweight …
-
Representation learning for computational sociopragmatics
… of discrete language symbols into a continuous representation space. The efficacy of these continuous representations is pivotal for developing successful NLP systems. With the advent of attention mechanisms, attention-based models have been adopted to learn contextual language representations …
-
Representation learning on complex data
Machine learning has enabled remarkable progress in various fields of research and application in recent years. The primary objective of machine learning consists of developing algorithms that can learn and improve through observation and experience. Machine learning algorithms learn from data, …
-
Representation learning on relational data
… interactions with other people. In many Machine Learning applications, we also know about relationships, which bear essential information for the use-case. Recommendations in social media, scene understanding in computer vision, or traffic prediction are few examples where relationships play a …
-
Unsupervised Representation Learning with Autoencoders
Despite the recent progress in machine learning and deep learning, unsupervised learning still remains a largely unsolved problem. It is widely recognized that unsupervised learning algorithms that can learn useful representations are needed for solving problems with limited label information. In …
-
Representation Learning under Limited Supervision
Recent advancements in machine learning have driven significant progress in visual representation learning, particularly through supervised methods relying on large-scale labelled datasets. However, the resource-intensive nature of acquiring and annotating such datasets poses challenges, especially …
-
Self-supervised video representation learning
… The goal of this thesis is to learn strong video representations efficiently via self-supervised learning: a method that learns from the data rather than human annotations.</p> <p>The thesis is structured around three themes: (1) self-supervised learning for short-term videos, (2) efficient video …
-
Representation Learning for Information Extraction
Distributed representations, predominantly acquired via neural networks, have been applied to natural language processing tasks including speech recognition and machine translation with a success comparable to sophisticated state-of-the-art algorithms. The present thesis offers an investigation of …
-
Foundations of Efficient Representation Learning
Representation learning extracts lower-dimensional, structured features from complex, unstructured data and reuses them across tasks. Despite strong empirical performance, its theoretical foundations remain limited. This thesis bridges this gap by developing formal efficiency guarantees for …
-
Deep representation learning on hypersphere
… is arguably one of the core problems in deep learning, since it can benefit a lot of downstream tasks such as visual recognition, object detection, semantic segmentation, etc. In this dissertation, we present a unified deep representation learning framework on hypersphere, which inherently …
-
Representation Learning for Web Intelligence
The excitement of web-driven machine learning research comes at two different granularity levels: on one hand, it enables us to model the complex interactions among web users and web components in the abstract; and on the other hand, it provides us with an automated means for comprehension of …
-
Graph representation learning for images
While a plurality of developments in AI still focus largely on Convolutional Neural Networks and Transformers, there has been frequent calls in the community towards building models with symbolic and relational processing capabilities. In our study we first reframe image classification as graph …
Page 1 of 55