Search for dissertations about: "Geometric Networks"
Showing result 6 - 10 of 36 swedish dissertations containing the words Geometric Networks.
-
6. G-equivariant convolutional neural networks
Abstract : Over the past decade, deep learning has revolutionized industry and academic research. Neural networks have been used to solve a multitude of previously unsolved problems and to significantly improve the state-of-the-art on other tasks, in some cases reaching superhuman levels of performance. READ MORE
-
7. Geometric Discretization in Shape analysis
Abstract : Discretizations in shape analysis is the main theme of this licentiate thesis, which comprises two papers. The first paper considers the problem of finding a parameterized time-dependent vector field that warps an initial set of points to a target set of points. READ MORE
-
8. Essays on Savings Behavior, Inflation Measurement, and Growth
Abstract : The Impact of Pension Reform on Household Income and Savings: A Quantitative Analysis of the Swedish CaseIncreases in life expectancy cause challenges for defined benefit pension systems. Sweden is one of few countries having undertaken a major reform aimed at creating a financially sustainable pension system. READ MORE
-
9. Geometric Supervision and Deep Structured Models for Image Segmentation
Abstract : The task of semantic segmentation aims at understanding an image at a pixel level. Due to its applicability in many areas, such as autonomous vehicles, robotics and medical surgery assistance, semantic segmentation has become an essential task in image analysis. READ MORE
-
10. Random geometric graphs and their applications in neuronal modelling
Abstract : Random graph theory is an important tool to study different problems arising from real world.In this thesis we study how to model connections between neurons (nodes) and synaptic connections (edges) in the brain using inhomogeneous random distance graph models. READ MORE