Sökning: "equivariant"
Visar resultat 1 - 5 av 15 avhandlingar innehållade ordet equivariant.
1. G-equivariant convolutional neural networks
Sammanfattning : 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. LÄS MER
2. Cohomology of arrangements and moduli spaces
Sammanfattning : This thesis mainly concerns the cohomology of the moduli spaces ℳ3[2] and ℳ3,1[2] of genus 3 curves with level 2 structure without respectively with a marked point and some of their natural subspaces. A genus 3 curve which is not hyperelliptic can be realized as a plane quartic and the moduli spaces ?[2] and ?1[2] of plane quartics without respectively with a marked point are given special attention. LÄS MER
3. Supersymmetric Localization : A Journey from Seven to Three Dimensions
Sammanfattning : Quantum Field Theory has been a dominating framework in elementary particle physics during the last century. Within this framework, supersymmetric theories have attracted a lot of attention due to their mathematical structure, simplicity and insight into the problems of unification, dark matter and hierarchy. LÄS MER
4. Mathematical Foundations of Equivariant Neural Networks
Sammanfattning : Deep learning has revolutionized industry and academic research. Over the past decade, 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. However, training a neural network typically requires large amounts of data and computational resources. LÄS MER
5. Equivariant Neural Networks for Biomedical Image Analysis
Sammanfattning : While artificial intelligence and deep learning have revolutionized many fields in the last decade, one of the key drivers has been access to data. This is especially true in biomedical image analysis where expert annotated data is hard to come by. LÄS MER