Advanced search
Showing result 6 - 10 of 899 essays matching the above criteria.
-
6. 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
-
7. Data Augmentation for Object Detection using Deep Reinforcement Learning
University essay from Lunds universitet/Institutionen för reglerteknikAbstract : Data augmentation is a concept which is used to improve machine learning models for computer vision tasks. It is usually done by firstly, defining a set of functions which transforms images and secondly, applying a random selection of these functions on the images. READ MORE
-
8. Mutual Enhancement of Environment Recognition and Semantic Segmentation in Indoor Environment
University essay fromAbstract : Background:The dynamic field of computer vision and artificial intelligence has continually evolved, pushing the boundaries in areas like semantic segmentation andenvironmental recognition, pivotal for indoor scene analysis. This research investigates the integration of these two technologies, examining their synergy and implicayions for enhancing indoor scene understanding. READ MORE
-
9. 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
-
10. Machine learning for molecular property prediction and drug safety
University essay from Göteborgs universitet/Institutionen för data- och informationsteknikAbstract : Utilizing machine learning methods for the prediction of acid dissociation (pKa ) values of compounds holds great significance, as pKa is an important parameter, optimized frequently in drug discovery. Accurate prediction of pKa values could potentially provide valuable insights on other molecular properties and thereby support compound design. READ MORE