Sökning: "Oövervakat lärande"

Visar resultat 11 - 15 av 17 uppsatser innehållade orden Oövervakat lärande.

1. 11. Unsupervised Learning of Useful and Interpretable Representations from Image Data

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

   Författare :Thomas Gaddy; [2019]
   Nyckelord :;

   Sammanfattning : This master thesis tackles the problem of unsupervised learning of useful and interpretable representations from image data using deep Convolutional Neural Networks (CNN). Recent years have seen remarkable success from using deep learning technologies to tackle computer vision problems. LÄS MER

3. 12. Text feature mining using pre-trained word embeddings

   Master-uppsats, KTH/Matematisk statistik

   Författare :Henrik Sjökvist; [2018]
   Nyckelord :Word embeddings; Feature engineering; Unsupervised learning; Deep learning; fast Text; Operational risk; Ordvektorer; Attributgenerering; Oövervakat lärande; Djupinlärning; fastText; Operativ risk;

   Sammanfattning : This thesis explores a machine learning task where the data contains not only numerical features but also free-text features. In order to employ a supervised classifier and make predictions, the free-text features must be converted into numerical features.  In this thesis, an algorithm is developed to perform that conversion. LÄS MER

4. 13. Unsupervised Anomaly Detection on Multi-Process Event Time Series

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

   Författare :Nicoló Vendramin; [2018]
   Nyckelord :Anomaly Detection; Recurrent Neural Networks; Time Series Analysis; Unsupervised Learning; Anomalitetsdetektering; Återkommande neurala nätverk; Tidsserieanalys; Oövervakat lärande;

   Sammanfattning : Establishing whether the observed data are anomalous or not is an important task that has been widely investigated in literature, and it becomes an even more complex problem if combined with high dimensional representations and multiple sources independently generating the patterns to be analyzed. The work presented in this master thesis employs a data-driven pipeline for the definition of a recurrent auto-encoder architecture to analyze, in an unsupervised fashion, high-dimensional event time-series generated by multiple and variable processes interacting with a system. LÄS MER

5. 14. Designing Variational Autoencoders for Image Retrieval

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

   Författare :Sara Torres Fernandez; [2018]
   Nyckelord :;

   Sammanfattning : The explosive growth of acquired visual data on the Internet has raised interestin developing advanced image retrieval systems. The main problem relies on thesearch of a specic image among large collections or databases, and this issue isshared by lots of users from a variety of domains, like crime prevention, medicineor journalism. LÄS MER

7. 15. Unsupervised Representation Learning with Clustering in Deep Convolutional Networks

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

   Författare :Mathilde Caron; [2018]
   Nyckelord :Computer vision; unsupervised learning;

   Sammanfattning : This master thesis tackles the problem of unsupervised learning of visual representations with deep Convolutional Neural Networks (CNN). This is one of the main actual challenges in image recognition to close the gap between unsupervised and supervised representation learning. LÄS MER