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 3277 for “"Interpretable"”.

  1. Interpretable multiple instance learning

    … understand how automated systems make decisions. Interpretable ML provides insight into the underlying reasoning behind AI and ML models while not stifling their predictive performance. Doing so is important for many reasons, such as facilitating trust, increasing transparency, and providing …

    soton Download PDF for Interpretable multiple instance learning (opens in a new tab)

  2. Interpretable Fake News Detection

    Fake news is one of the most serious challenges facing the news industry today, which could result in adverse impacts on our society. Recent progress of deep neural networks (DNNs) has shown some promising results in detecting fake news. However, a critical missing piece of such detection is the …

    tamu Repository record for Interpretable Fake News Detection (opens in a new tab)

  3. Interpretable computational metaphor processing

    … by developing computational methodologies for interpretable metaphor processing, bridging insights from computational linguistics, psycholinguistics, and artificial intelligence. The work advances three core areas: 1)Enhancing metaphor detection through syntactic pruning (RoPPT), semantic frame …

    whiterose Download PDF for Interpretable computational metaphor processing (opens in a new tab)

  4. Towards Interpretable Vision Systems

    … instead of identifying errors, we develop more interpretable AI systems, which reveal the inner modules directly. We take two tasks as examples, words semantic matching and Visual Question Answering (VQA). In VQA, we take binary questions on abstract scenes as the first stage, then we extend to …

    vt Repository record for Towards Interpretable Vision Systems (opens in a new tab)

  5. Interpretable local citation recommendation

    Submission original under an indefinite embargo labeled 'Open Access'. The submission was exported from vireo on 2024-09-16 without embargo terms

    uiuc Repository record for Interpretable local citation recommendation (opens in a new tab)

  6. Towards interpretable face recognition

    … recognition, we report our efforts towards interpretable face recognition. We propose a spatial activation diversity loss to learn more structured face representations. By leveraging the structure, we further design a feature activation diversity loss to push the interpretable …

    msu Repository record for Towards interpretable face recognition (opens in a new tab)

  7. Interpretable Multi-hop Question Answering

    … computers to answer multi-hop questions in an interpretable fashion using an acceptable reasoning pattern. This thesis attempts to tackle two distinct problems: i) how to build an interpretable QA system to answer a complex multi-hop question; ii) how to learn knowledge for the new QA tasks …

    auckland-ms Repository record for Interpretable Multi-hop Question Answering (opens in a new tab)

  8. Interpretable modelling with sparse kernels

    … thesis is the development of advanced non-linear interpretable models. Interpretable modelling offers us a powerful tool with which to understand the structure of a model constructed from data, allowing model validation and assisting in model selection. Gibbs (1997) observes the easiest way to …

    soton Download PDF for Interpretable modelling with sparse kernels (opens in a new tab)

  9. Statistical Approaches for Interpretable Radiomics

    … to move away from black box methods towards more interpretable approaches. In this thesis, we present two projects that aim to address the need for meaningful features in radiomic analyses. In the first project, we develop a hierarchical tree structure on the image pixels, creating a feature that …

    rice Repository record for Statistical Approaches for Interpretable Radiomics (opens in a new tab)

  10. Interpretable Machine Learning And Applications

    … fundamental works and recent advancements in the interpretable machine learning research domain in Chapter 1. In Chapter 2, we tackle the interpretability problem in recommender systems by designing and implementing a feature mapping strategy into the recommender systems, so-called Attentive …

    wayne-thes Repository record for Interpretable Machine Learning And Applications (opens in a new tab)

  11. Interpretable Fine-Grained Visual Categorization

    Not all categories are created equal in object recognition. Fine-grained visual categorization (FGVC) is a branch of visual object recognition that aims to distinguish subordinate categories within a basic-level category. Examples include classifying an image of a bird into specific species like …

    byu Repository record for Interpretable Fine-Grained Visual Categorization (opens in a new tab) Download PDF for Interpretable Fine-Grained Visual Categorization (opens in a new tab)

  12. Tree Models for Interpretable Agents

    … training agents themselves, which provides an interpretable grounding for learnt behaviour. Furthermore, we show how reward trees can be learnt from human feedback, thereby drawing a connection between interpretability and the literature on human-agent alignment. We establish the efficacy of …

    bristol Repository record for Tree Models for Interpretable Agents (opens in a new tab) Download PDF for Tree Models for Interpretable Agents (opens in a new tab)

  13. Extracting Interpretable Equations from Data

    Expressing relationships within data using mathematical formulas lies at the centre of scientific discovery. In recent years symbolic regression has been proposed as a tool for discovering relationships in data in order to convey information regarding system dynamics. In this study an algorithm for …

    chalmers Repository record for Extracting Interpretable Equations from Data (opens in a new tab)

  14. Interpretable Models for Information Extraction

    There is an abundance of information being generated constantly, most of it encoded as unstructured text. The information expressed this way, although publicly available, is not directly usable by computer systems because it is not organized according to a data model that could inform us how …

    arizona-thes Repository record for Interpretable Models for Information Extraction (opens in a new tab)

  15. Clinically interpretable models for healthcare data

    … investigates the development of clinically interpretable models for EHR data using dimensionality reduction techniques. We posit that clinical concepts are representations in lower dimensional latent spaces. Yet, standard dimensionality reduction techniques alone are insufficient to derive …

    texas Repository record for Clinically interpretable models for healthcare data (opens in a new tab)

  16. Robust, interpretable, and usable entity representations

    … aspects. Interpretability: we first design interpretable entity representations where each entity is represented as a set of concepts (i.e., entity types) and their associated probabilities. Since these entity representations possess characteristics of both discrete and continuous features, …

    texas Repository record for Robust, interpretable, and usable entity representations (opens in a new tab)

  17. Interpretable generative models for precipitation forecasting

    Accurate and reliable rainfall forecasting is crucial for making informed decisions across various domains, particularly in climate science and agricultural management. We aimed to enhance the explainability of generative models used in climate science applications, focusing on short to …

    texas Repository record for Interpretable generative models for precipitation forecasting (opens in a new tab)

  18. Interpretable Approaches to Dependent Structure Learning

    … example, in biomedicine), approaches tailored to interpretable and integrative analysis have recently come into focus. The need for such methods is heavily underscored by rapid developments in biological, medical and public health technology. In these areas, we are collecting increasingly diverse …

    jhu Repository record for Interpretable Approaches to Dependent Structure Learning (opens in a new tab)

Page 1 of 164