Sökning: "Syntetisk"
Visar resultat 6 - 10 av 238 uppsatser innehållade ordet Syntetisk.
6. Mitigating Unintended Bias in Toxic Comment Detection using Entropy-based Attention Regularization
Master-uppsats, KTH/Skolan för elektroteknik och datavetenskap (EECS)Sammanfattning : The proliferation of hate speech is a growing challenge for social media platforms, as toxic online comments can have dangerous consequences also in real life. There is a need for tools that can automatically and reliably detect hateful comments, and deep learning models have proven effective in solving this issue. LÄS MER
7. Evaluating the Viability of Synthetic Pre-training Data for Face Recognition Using a CNN-Based Multiclass Classifier
Kandidat-uppsats, KTH/Skolan för elektroteknik och datavetenskap (EECS)Sammanfattning : Today, face recognition is becoming increasingly accurate and faster with deep learning methods such as convolutional neural networks (CNNs), and is now widely used in areas such as security and entertainment. Typically, these CNNs are trained using real-face datasets like CASIA-WebFace, which was put together using web-crawling of IMDB. LÄS MER
8. Läsinlärningsmetoder : Vilka metoder används i praktiken?
Uppsats för yrkesexamina på avancerad nivå, Mälardalens universitet/Akademin för utbildning, kultur och kommunikationSammanfattning : Syftet med föreliggande studie är att undersöka vilka läsinlärningsmetoder som används av F-3 lärare i en mellansvensk stad. Studien är kvantitativ och genomfördes med enkäter som skickades ut till ca 490 lärare som undervisar elever i F-3. Ramfaktorteorin är vald som teoretiskt perspektiv i studien. LÄS MER
9. Towards an open, automated, and reproducible synthetic population of Switzerland : A preparatory, modular pipeline for agent-based mobility simulations
Master-uppsats, KTH/Transport och systemanalysSammanfattning : This thesis explores the development of an automated re-synthesising tool, called EasySynth, to generate a Swiss synthetic population and travel diaries from publicly available data. The aim is to overcome the limitations of restricted-access real population data while maintaining control over anonymisation and statistical accuracy. LÄS MER
10. LiDAR Perception in a Virtual Environment Using Deep Learning : A comparative study of state-of-the-art 3D object detection models on synthetic data
Master-uppsats, KTH/Skolan för elektroteknik och datavetenskap (EECS)Sammanfattning : Perceiving the environment is a crucial aspect of autonomous vehicles. To plan the route, the autonomous vehicle needs to be able to detect objects such as cars and pedestrians. This is possible through 3D object detection. However, labeling this type of data is time-consuming. LÄS MER