Sökning: "transformeringsmodeller"

Hittade 1 uppsats innehållade ordet transformeringsmodeller.

  1. 1. Classifying and Comparing Latent Space Representation of Unstructured Log Data.

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

    Författare :Bharat Sharma; [2021]
    Nyckelord :Machine learning; Natural language processing; Deep learning; Classification; Supervised learning; Transformer models; Sentence embeddings; Doc2Vec; Deep averaging networks.; Maskininlärning; naturligtspråkbehandling; djupinlärning; klassificering; övervakad inlärning; transformeringsmodeller; meningsinbäddningar; Doc2Vec; djupa linjärkombinerande nätverk.;

    Sammanfattning : This thesis explores and compares various methods for producing vector representation of unstructured log data. Ericsson wanted to investigate machine learning methods to analyze logs produced by their systems to reduce the cost and effort required for manual log analysis. LÄS MER