Advanced search
Showing result 1 - 5 of 389 essays matching the above criteria.
-
1. Self-Supervised Learning for Tabular Data: Analysing VIME and introducing Mix Encoder
University essay from Lunds universitet/Fysiska institutionenAbstract : We introduce Mix Encoder, a novel self-supervised learning framework for deep tabular data models based on Mixup [1]. Mix Encoder uses linear interpolations of samples with associated pretext tasks to form useful pre-trained representations. READ MORE
-
2. A Simulation Game Approach for Improving Access to Specialized Healthcare Services in Sweden
University essay from KTH/Medicinteknik och hälsosystemAbstract : In Sweden, where a decentralized healthcare system is applied, all patients are registered at a primary healthcare center. To access most of the publicly funded specialized care clinics, patients need to be referred by a general physician at the primary healthcare center. READ MORE
-
3. Exploring adaptation of self-supervised representation learning to histopathology images for liver cancer detection
University essay from Luleå tekniska universitet/Institutionen för system- och rymdteknikAbstract : This thesis explores adapting self-supervised representation learning to visual domains beyond natural scenes, focusing on medical imaging. The research addresses the central question: "How can self-supervised representation learning be specifically adapted for detecting liver cancer in histopathology images?" The study utilizes the PAIP 2019 dataset for liver cancer segmentation and employs a self-supervised approach based on the VICReg method. READ MORE
-
4. Planet-NeRF : Neural Radiance Fields for 3D Reconstruction on Satellite Imagery in Season Changing Environments
University essay from Linköpings universitet/DatorseendeAbstract : This thesis investigates the seasonal predictive capabilities of Neural Radiance Fields (NeRF) applied to satellite images. Focusing on the utilization of satellite data, the study explores how Sat-NeRF, a novel approach in computer vision, per- forms in predicting seasonal variations across different months. READ MORE
-
5. POTENTIALS FOR LEARNING IN THE DESIGN OF DIGITAL TEXTBOOKS
University essay from Göteborgs universitet/Institutionen för pedagogik, kommunikation och lärandeAbstract : Purpose: The aim of this study was to enhance the knowledge of the learning potentials associated with the different designs of digital textbooks and their implications for the representation of historical content. More specifically, the analysis focused on four Finnish digital history textbooks, with the Winter War being selected as the specific learning unit due to its significant role in the history of Finland. READ MORE
