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 11 of 11 for “"Class discovery"”.

  1. Class discovery via feature selection in unsupervised settings

    … statistical "large p small n" problem. The class or cluster identification is based on the clinical information associated with the type or subtype of the cancer (either known or unknown) for each individual. We discuss and develop novel feature ranking methods, which complement and build …

    bu Repository record for Class discovery via feature selection in unsupervised settings (opens in a new tab)

  2. Novel Class Discovery for 3D Point Cloud Semantic Segmentation in Large-Scale Environments

    … categories. This dissertation addresses novel class discovery (NCD) in large-scale 3D point cloud segmentation through geometry-aware mechanisms, adaptive multi-source fusion, and hybrid supervision frameworks. The first study establishes geometric foundations through voxel-geometry integration …

    waterloo Repository record for Novel Class Discovery for 3D Point Cloud Semantic Segmentation in Large-Scale Environments (opens in a new tab)

  3. Contrastive Filtering And Dual-Objective Supervised Learning For Novel Class Discovery In Document-Level Relation Extraction

    … natural language processing focused on the classification of relationships between entities in a given text. Primary applications of RE can be seen in various contexts such as knowledge graph construction and question answering systems. Traditional approaches to RE tend towards the …

    calpoly Repository record for Contrastive Filtering And Dual-Objective Supervised Learning For Novel Class Discovery In Document-Level Relation Extraction (opens in a new tab)

  4. Clustering Cancer Tumours using Unsupervised Deep Learning Techniques

    … deep learning techniques may be used as a class discovery method analysing cancer tumour data. Furthermore, the possibility of inferring which genes most strongly contribute in the differentiation of cancer types is discussed. Gene expression data from The Cancer Genome Atlas of 10 …

    chalmers Repository record for Clustering Cancer Tumours using Unsupervised Deep Learning Techniques (opens in a new tab)

  5. A nonparametric Bayesian perspective for machine learning in partially-observed settings

    … may even have an evolving nature introducing new classes continually. This constitutes a partially-observed setting, where it would be impractical to obtain a labeled data set exhaustively defined by a fixed set of classes. Traditional supervised learning algorithms, assuming an exhaustive …

    iupui Repository record for A nonparametric Bayesian perspective for machine learning in partially-observed settings (opens in a new tab)

  6. Ontology-led molecular classification of colorectal cancer uncovers distinct tumour subtypes with therapeutic and clinical relevance

    … accessing the published gene signatures, a new classification system was developed that defines pathway-driven tumours for patient stratification and tested its prognostic value.<br/><br/>A transcriptional breast cancer (BC) originated DNA Damage Immune Response (DDIR) assay, revealed …

    qu-belfast Repository record for Ontology-led molecular classification of colorectal cancer uncovers distinct tumour subtypes with therapeutic and clinical relevance (opens in a new tab) Download PDF for Ontology-led molecular classification of colorectal cancer uncovers distinct tumour subtypes with therapeutic and clinical relevance (opens in a new tab)

  7. Influence of the input data on learning deep representations

    … thesis studies, through the prism of image classification, the influence of the input data on learning deep representations. Indeed, data is abundant but also multifaceted: samples might come from a single or multiple domains, or they can also be more or less labelled. We show in this thesis …

    oxford Repository record for Influence of the input data on learning deep representations (opens in a new tab)

  8. Knowledge transfer and retention in deep neural networks

    This thesis addresses the crucial problem of knowledge transfer and retention in deep neural networks. The ability to transfer knowledge from previously learned tasks and retain it for future use is essential for machine learning models to continually adapt to new tasks and improve their overall …

    trento Repository record for Knowledge transfer and retention in deep neural networks (opens in a new tab)

  9. Microarray-based Multiclass Classification using Relative Expression Analysis

    … gene expression-based biological markers for class discovery and prediction of complex diseases such as cancer. For example, expression patterns of genes are discovered to be associated with phenotypes (e.g., classes of disease) through statistical learning models. Early hopes that …

    jhu Repository record for Microarray-based Multiclass Classification using Relative Expression Analysis (opens in a new tab)

  10. Semi-supervised learning for acoustic and prosodic modeling in speech applications

    … learning framework for the problem of phone classification, phone recognition and prosody detection. The proposed approach will be particularly useful in the case where recognition performance is limited by the amount of transcribed data. In the first part of the thesis, we investigate …

    uiuc Repository record for Semi-supervised learning for acoustic and prosodic modeling in speech applications (opens in a new tab)

  11. GENERALIZABLE SCENE UNDERSTANDING

    Scene understanding is a fundamental research area in computer vision, with applications in autonomous driving, surveillance systems, AI assistants, and AI-generated content. While modern deep neural networks have achieved remarkable success under fully supervised settings, they often suffer from …

    nus Repository record for GENERALIZABLE SCENE UNDERSTANDING (opens in a new tab) Download file for GENERALIZABLE SCENE UNDERSTANDING (opens in a new tab)