Sökning: "oövervakad klassificering"
Visar resultat 1 - 5 av 9 uppsatser innehållade orden oövervakad klassificering.
1. Distance preserving Fermat VAE
Master-uppsats, KTH/Skolan för elektroteknik och datavetenskap (EECS)Sammanfattning : Deep neural networks takes their strength in the representations, or features, that they internally build. While these internal encodings help networks performing classification or regression tasks on specific data types, it exists a branch of machine learning that has for only purpose to build these representations. LÄS MER
2. BERT Language Modelling on Network Log Data for Generalized Unsupervised Intrusion Detection
Master-uppsats, KTH/Skolan för elektroteknik och datavetenskap (EECS)Sammanfattning : Intrusion detection is the most prominent topic of modern computer network security. The potential attack surface is growing exponentially every year. To cope with the amounts of data which accrue, automated methods for detecting undesired network activity are the only feasible solution. LÄS MER
3. Abnormality detection in diagnostics data from network cameras
Master-uppsats, Lunds universitet/Matematik LTHSammanfattning : For data-driven companies, there is a need to efficiently navigate through big quantities of collected data. In our case; detecting changes in the behaviour of data. We have investigated whether machine learning could be applied to automate the process of finding abnormal behaviour (anomalies) in collected data. LÄS MER
4. A comparative study on the unsupervised classification of rat neurons by their morphology
Kandidat-uppsats, KTH/Skolan för elektroteknik och datavetenskap (EECS)Sammanfattning : An ongoing problem regarding the automatic classification of neurons by their morphology is the lack of consensus between experts on neuron types. Unsupervised clustering using persistent homology as a descriptor for the morphology of neurons helps tackle the problem of bias in feature selection and has the potential of aiding neuroscience research in developing a framework for automatic neuron classification. LÄS MER
5. Robust Descriptor Learning Using Variational Auto-Encoders
Master-uppsats, KTH/Skolan för elektroteknik och datavetenskap (EECS)Sammanfattning : Image matching is the task of finding points in one image corresponding to the same points in the other image. Classical feature descriptors fail to match points when the images are under extreme viewpoint or seasonal changes. This thesis tackles the problem of image matching when two images are under severe changes. LÄS MER
