Sökning: "Oövervakat lärande"

Visar resultat 16 - 17 av 17 uppsatser innehållade orden Oövervakat lärande.

  1. 16. Anomaly Detection for Temporal Data using Long Short-Term Memory (LSTM)

    Master-uppsats, KTH/Skolan för informations- och kommunikationsteknik (ICT)

    Författare :Akash Singh; [2017]
    Nyckelord :LSTM; RNN; anomaly detection; time series; deep learning; LSTM; RNN; avvikelsedetektion; tidsserier; djupt lärande;

    Sammanfattning : We explore the use of Long short-term memory (LSTM) for anomaly detection in temporal data. Due to the challenges in obtaining labeled anomaly datasets, an unsupervised approach is employed. We train recurrent neural networks (RNNs) with LSTM units to learn the normal time series patterns and predict future values. LÄS MER

  3. 17. Redundant and Irrelevant Attribute Elimination using Autoencoders

    Master-uppsats, KTH/Skolan för datavetenskap och kommunikation (CSC)

    Författare :Tim Granskog; [2017]
    Nyckelord :autoencoder dimensionality reduction attribute elimination;

    Sammanfattning : Real-world data can often be high-dimensional and contain redundant or irrelevant attributes. High-dimensional data are problematic for machine learning as the high dimensionality causes learning to take more time and, unless the dataset is sufficiently large to provide an ample number of samples for each class, the accuracy will suffer. LÄS MER