Sökning: "Träning inlärning"
Visar resultat 21 - 25 av 111 uppsatser innehållade orden Träning inlärning.
21. Instability of a bi-directional TiFGAN in unsupervised speech representation learning
Master-uppsats, KTH/Skolan för elektroteknik och datavetenskap (EECS)Sammanfattning : A major challenge in the application of machine learning in the speech domain is the unavailability of annotated data. Supervised machine learning techniques are highly dependent on the amount of labelled data and the quality of the labels. LÄS MER
22. Transfer learning techniques in time series analysis
Master-uppsats, KTH/Skolan för elektroteknik och datavetenskap (EECS)Sammanfattning : Deep learning works best with vast andd well-distributed data collections. However, collecting and annotating large data sets can be very time-consuming and expensive. Moreover, deep learning is specific to domain knowledge, even with data and computation. E. LÄS MER
23. Tygelspänningens påverkan på hästens beteende
Kandidat-uppsats, SLU/Dept. of Anatomy, Physiology and BiochemistrySammanfattning : Denna studie fördjupar sig i tygelspänning och hur denna påverkar hästens beteende samt vilka oönskade beteenden som uppkommer i samband med träning. Andra studier har visat att orsaken till oönskade beteenden kan bero på olika typer av bett, ryttarens kunskap samt vilka metoder som används för att träna hästen. LÄS MER
24. Complementary Labels and Their Impact on Deep Learning of a Target Class : Evaluated on Object Detection in the Low Data Regime
Master-uppsats, KTH/Skolan för elektroteknik och datavetenskap (EECS)Sammanfattning : In specialized object detection tasks and domains, it is sometimes only possible to collect and annotate a small amount of data for training and evaluation, which constrains training to a low data regime that can lead to poor generalization. In this thesis, the impact of annotations from additional classes, referred to as complementary labels, when learning a target class is studied as a potential approach to improve performance in the low data regime, for object detection. LÄS MER
25. On the Efficiency of Transfer Learning in a Fighter Pilot Behavior Modelling Context
Master-uppsats, KTH/Matematik (Inst.)Sammanfattning : Creating realistic models of human fighter pilot behavior is made possible with recent deep learning techniques. However, these techniques are often highly dependent on large datasets, often unavailable in many settings, or expensive to produce. LÄS MER