Sökning: "noisy labels"

Visar resultat 1 - 5 av 10 uppsatser innehållade orden noisy labels.

  1. 1. Information Extraction for Test Identification in Repair Reports in the Automotive Domain

    Master-uppsats, Uppsala universitet/Institutionen för lingvistik och filologi

    Författare :Huang Jie; [2023]
    Nyckelord :text classification; information retrieval; contrastive learning; prompt-based fine-tuning; large language models;

    Sammanfattning : The knowledge of tests conducted on a problematic vehicle is essential for enhancing the efficiency of mechanics. Therefore, identifying the tests performed in each repair case is of utmost importance. This thesis explores techniques for extracting data from unstructured repair reports to identify component tests. LÄS MER

  3. 2. Unsupervised Clustering of Behavior Data From a Parking Application : A Heuristic and Deep Learning Approach

    Uppsats för yrkesexamina på avancerad nivå, Umeå universitet/Institutionen för matematik och matematisk statistik

    Författare :Edvard Magnell; Joakim Nordling; [2023]
    Nyckelord :ML; Machine learning; clustering; unsupervised learning; deep learning; autoencoder; AI; artificial intelligence;

    Sammanfattning : This report aims to present a project in the field of unsupervised clustering on human behavior in a parking application. With increasing opportunities to collect and store data, the demands to utilize the data in meaningful ways also increase. LÄS MER

  4. 3. Cell Identification from Microscopy Images using Deep Learning on Automatically Labeled Data

    Master-uppsats, Lunds universitet/Institutionen för elektro- och informationsteknik

    Författare :Fredrik Salomon-Sörensen; [2023]
    Nyckelord :Deep Learning; Cell Identification; Image Segmentation; Nuclei Segmentation; Convolutional Neural Networks; UNet; Image Analysis; Microscopy; Noisy Labels; Phase-Contrast; Automatic Labeling; Technology and Engineering;

    Sammanfattning : In biology, cell counting provides a fundamental metric for live-cell experiments. Unfortunately, most researchers are constrained to using tedious and invasive methods for counting cells. Automatic identification of cells in microscopy images would therefore be a valuable tool for such researchers. LÄS MER

  5. 4. The effect of model calibration on noisy label detection

    Master-uppsats, KTH/Skolan för elektroteknik och datavetenskap (EECS)

    Författare :Max Joel Söderberg; [2023]
    Nyckelord :Area Under the Margin; Calibration; Image classification; Label smoothing; Noisy labels; Overconfidence; Area under marginalen; Kalibrering; Bildklassificering; Etikettutjämning; Brusiga etiketter; Övertro;

    Sammanfattning : The advances in deep neural networks in recent years have opened up the possibility of using image classification as a valuable tool in various areas, such as medical diagnosis from x-ray images. However, training deep neural networks requires large amounts of annotated data which has to be labelled manually, by a person. LÄS MER

  7. 5. Machine Learning for Improving Detection of Cooling Complications : A case study

    Master-uppsats, KTH/Industriell produktion

    Författare :William Bruksås Nybjörk; [2022]
    Nyckelord :Temperature controllable containers; Machine Learning; imbalanced data; data analysis; noisy labels; feature engineering; threshold tuning;

    Sammanfattning : The growing market for cold chain pharmaceuticals requires reliable and flexible logistics solutions that ensure the quality of the drugs. These pharmaceuticals must maintain cool to retain the function and effect. Therefore, it is of greatest concern to keep these drugs within the specified temperature interval. LÄS MER