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 4 of 4 for “"Imperfect labels"”.

  1. Computational Techniques to Identify Rare Events in Spatio-temporal Data

    … and (2) classification enhancement of existing imperfect classification maps using physics-guided constraints. We study the problem of identifying land cover changes such as forest fires as a supervised binary classification task with the following characteristics: (i) instead of true labels …

    umn Repository record for Computational Techniques to Identify Rare Events in Spatio-temporal Data (opens in a new tab)

  2. Uncertainty aware classification: augmenting classifiers to handle uncertainty

    … most classifiers are not robust against imperfect labels. However, annotation processes are usually expensive, hindering the amount of labels that are collected. One possible solution is to alleviate the annotation process in order to accept weak labels instead. Nonetheless, the resulting …

    bristol Repository record for Uncertainty aware classification: augmenting classifiers to handle uncertainty (opens in a new tab) Download PDF for Uncertainty aware classification: augmenting classifiers to handle uncertainty (opens in a new tab)

  3. Understanding Deep Learning via Tractable Models

    … generalization where a student model trained on imperfect labels generated by a weaker teacher nonetheless surpasses that teacher. This phenomenon has been widely observed but the mechanisms that enable it have remained poorly understood. In this chapter, through a theoretical analysis of simple …

    penn Repository record for Understanding Deep Learning via Tractable Models (opens in a new tab)

  4. Modeling Infrequent Events by Integrating Noisy Data From Multiple Sources And Applying Machine Learning to Classify and Predict Disruptions

    … that function effectively despite missing data, imperfect labels, and extreme class imbalance. In this dissertation, five studies address this challenge by augmenting limited primary signals with supplementary information sources, fusing the heterogeneous evidence within architectures that …

    temple Repository record for Modeling Infrequent Events by Integrating Noisy Data From Multiple Sources And Applying Machine Learning to Classify and Predict Disruptions (opens in a new tab)