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 27 for “"Learning representations"”.
-
Meta-learning representations with relational structure
Representation learning has emerged as a versatile tool that is able to take advantage of the vast datasets acquired using digital technologies. The broad applicability of this method stems from its flexibility in use as a subsystem and malleability in incorporating priors in model architectures. …
-
Learning Representations for Limited and Heterogeneous Medical Data
… heterogeneity are challenges of representation learning for machine learning in medicine due to the diversity of medical data and the expense of data collection and annotation. To learn generalizable representations from such limited and heterogeneous medical data, we aim to utilize various …
-
Learning representations for information mining from text corpora with applications to cyber threat intelligence
This research develops learning representations and architectures for natural language understanding, within an information mining framework for analysis of open-source cyber threat intelligence (CTI). Both contextual (sequential) and topological (graph-based) encodings of short text documents are …
-
Improving Generative Models for 3D Molecular Structures
… and published at the International Conference on Learning Representations (ICLR), 2024.
-
Rewriting the Rules of a Classifier
… indicate that deep networks may be spontaneously learning representations of concepts with semantic meaning, and encoding a relational structure or rule between these concepts. We refer to these encoded relationships between concepts in the network as rules. In classifiers, we rewrite an existing …
-
Learning digits via joint audio-visual representations
Our goal is to explore models for language learning in the manner that humans learn languages as children. Namely, children do not have intermediary text transcriptions in correlating visual and audio inputs from the environment; rather, they directly make connections between what they see and what …
-
Disentangling neural network representations for improved generalization
… which can help preven neural networks from learning representations that capture spurious patterns that do not generalize past the training data, and instead encourage them to capture factors of variation that explain the data generally. In this thesis we identify three kinds of …
-
Bayesian nonparametric approaches for reinforcement learning in partially observable domains
… while simultaneously performing the task. Learning a representation for a task also involves a trade-off between modeling the data that we have seen previously and being able to make predictions about new data streams. In this thesis, we explore one approach for learning representations of …
-
Similarity and explanation for dynamic telecommunication engineer support.
… of Case-Based Reasoning (CBR) systems, but learning representations optimised for similarity comparisons can be difficult. CBR systems typically rely on separate algorithms to learn representations for cases and to compare those representations, as symbolised by the vocabulary and similarity …
-
Motifs, binding, and expression : computational studies of transcriptional regulation
… protein localization, and expression data: (1) learning representations of the specific binding interactions that determine connectivity in regulatory networks, (2) developing physically grounded models describing these interactions, and (3) relating binding to its ultimate effect on the …
-
Exploiting Cross-Lingual Representations For Natural Language Processing
Traditional approaches to supervised learning require a generous amount of labeled data for good generalization. While such annotation-heavy approaches have proven useful for some Natural Language Processing (NLP) tasks in high-resource languages (like English), they are unlikely to scale to …
-
Finding Sparse Subnetworks in Self-Supervised Speech Recognition and Speech Synthesis
… self-supervised speech representation learning models typically consists of more than 300M model parameters and being trained on 24 GPUs. While such a paradigm has proven to be effective in certain offline settings, it remains unclear the extent to which it can be extended to online and …
-
Self-Supervised Learning for Speech Processing
Deep neural networks trained with supervised learning algorithms on large amounts of labeled speech data have achieved remarkable performance on various spoken language processing applications, often being the state of the arts on the corresponding leaderboards. However, the fact that training …
-
Representation learning on heterogeneous spatiotemporal networks
<p>“The problem of learning latent representations of heterogeneous networks with spatial and temporal attributes has been gaining traction in recent years, given its myriad of real-world applications. Most systems with applications in the field of transportation, urban economics, medical …
-
Evolving Network Representation Learning Based on Random Walks
… Lately, there is a fast-growing interest in learning low-dimensional continuous representations of networks that can be utilized to perform highly accurate and scalable graph mining tasks. A family of these methods is based on performing random walks on a network to learn its structural …
-
Identifiable Causal Representation Learning: Unsupervised, Multi-View, and Multi-Environment
… together ideas from causality and representation learning. Causal models provide rich descriptions of complex systems as sets of mechanisms by which each variable is influenced by its direct causes. They support reasoning about manipulating parts of the system, capture a whole range of …
-
Representation learning in multi-dimensional clinical timeseries for risk and event prediction
… noisy data. In this work, we present machine learning methods that distill large amounts of heterogeneous health data into latent state representations. These representations are then used to estimate risks of poor outcomes, and response to intervention in multivariate physiological signals. …
-
Towards robust and domain invariant feature representations in Deep Learning
… perception-based systems is to define and learn representations of the scene that are more robust and adaptive to several nuisance factors. Over the recent past, for a variety of tasks involving images, learned representations have been empirically shown to outperform handcrafted ones. However, …
Page 1 of 2