Current jobs related to PhD Position in Mathematics: Geometric Deep Learning at Umeå University - Umeå, Västerbotten - Euro Math Soc
-
PhD Position in Geometric Deep Learning
2 weeks ago
Umeå, Västerbotten, Sweden Umeå University Full timeProject OverviewThe project aims to deepen the mathematical theory of geometric deep learning. This involves developing new ways of constructing equivariant networks, describing the resulting models mathematically, and analyzing how symmetries affect the training of neural networks.Key ResponsibilitiesConduct research in geometric deep learning and its...
-
Umeå, Västerbotten, Sweden Umeå University Full timeProject OverviewThe project aims to deepen the mathematical theory of geometric deep learning, a subfield of neural network theory that concerns symmetries in data or learning tasks and constructing neural networks that react properly to them.Key Research QuestionsDevelopment of new ways of constructing equivariant networksDescription of the resulting models...
-
Umeå, Västerbotten, Sweden Umeå University Full timeProject Overview:Geometric deep learning is a rapidly growing field that combines the power of neural networks with the mathematical beauty of symmetry. As a PhD student in this project, you will delve into the theoretical foundations of equivariant networks, exploring how symmetries can be leveraged to improve the performance of deep learning...
-
Umeå, Västerbotten, Sweden Umeå University Full timeProject OverviewThe project aims to deepen the mathematical theory of geometric deep learning, a subfield within neural network theory that concerns symmetries in data or learning tasks and constructing neural networks that react properly to them.Research QuestionsDevelop new ways of constructing equivariant networksDescribe the resulting models...
-
Mathematical Researcher in Geometric Deep Learning
2 months ago
Umeå, Västerbotten, Sweden Umeå University Full timeProject OverviewThe project aims to deepen the mathematical theory of geometric deep learning, a subfield of neural network theory that concerns symmetries in data or learning tasks and constructing neural networks that react properly to them.Research QuestionsDevelop new ways of constructing equivariant networksDescribe the resulting models...
-
Umeå, Västerbotten, Sweden Umeå University Full timeProject OverviewWe are seeking a highly motivated and skilled PhD student to join our team at Umeå University in the field of deep-learning conifer genomics. The successful candidate will be involved in the development of novel deep-learning driven computational tools for efficient identification of transposable elements in large plant genomes.Research...
-
Umeå, Västerbotten, Sweden Umeå University Full timeProject OverviewAs a PhD student in plant science, you will contribute to the development of deep-learning driven computational tools for efficient identification of transposable elements in large plant genomes. This project aims to advance our understanding of the complexities of transposable elements in plant genomes and their impact on genome...
-
Umeå, Västerbotten, Sweden Umeå University Full timeProject OverviewAs part of our ongoing research in plant genomics, we are seeking a highly motivated PhD student to join our team at Umeå University. The successful candidate will work on developing deep-learning driven computational tools for efficient identification of transposable elements (TEs) in large plant genomes.Research ObjectivesDevelop new...
-
Umeå, Västerbotten, Sweden Umeå University Full timeProject OverviewAdvances in high-throughput DNA sequencing technologies have led to the production of large genome assemblies, including those of conifers, wheat, axolotl salamanders, and giant lungfish. Genome annotation, particularly the identification of transposable elements (TEs), presents a significant challenge in analyzing these large genomes. Deep...
-
PhD Researcher in Data Privacy
2 months ago
Umeå, Västerbotten, Sweden Umeå University Full timeAbout the ProjectThe project aims to develop privacy-aware machine learning models that are explainable and extracted from complex and heterogeneous data. We are interested in building models that provide provenance, interpretability, and transparency. Within explainable machine learning, we focus on topics such as:Provenance: understanding the origin and...
-
PhD Researcher in Data Privacy
1 month ago
Umeå, Västerbotten, Sweden Umeå University Full timeProject OverviewThe project aims to develop privacy-aware machine learning models that are explainable and extracted from complex and heterogeneous data. We are interested in building models that provide transparency and interpretability, as well as different types of privacy measures and models.Research GroupThe research group is part of the Computing...
-
PhD Researcher in Data Privacy
2 months ago
Umeå, Västerbotten, Sweden Umeå University Full timeProject OverviewThe project aims to develop privacy-aware machine learning models that are explainable and extracted from complex and heterogeneous data. We are interested in building models that provide provenance, interpretable, and transparent results. Within explainable machine learning, we focus on topics such as provenance, interpretable, and...
-
Umeå, Västerbotten, Sweden Umeå University Full timeProject OverviewThe project focuses on plant genomics and the development of deep-learning driven computational tools. The goal is to develop new deep-learning driven transposable elements (TEs) identification tools to further decrease the computational demand for large genome analysis.Key ObjectivesDevelop a comprehensive TE dataset to capture the sequence...
-
PhD Researcher in Data Privacy
2 weeks ago
Umeå, Västerbotten, Sweden Umeå University Full timeProject OverviewThe project aims to develop privacy-aware machine learning models that are explainable and extracted from complex and heterogeneous data. We are interested in building models that provide provenance, interpretability, and transparency. Within explainable machine learning, we are interested in topics such as provenance, interpretable, and...
-
PhD Position in Experimental Physics
4 weeks ago
Umeå, Västerbotten, Sweden Umeå University Full timeResearch Project: Ultrafast NanoscienceThe Ultrafast Nanoscience group at Umeå University invites applications for a PhD position in experimental physics. The project focuses on understanding the dynamics of electronic degrees of freedom in nanostructured materials using ultrafast spectroscopy and plasmonic excitations.Key Responsibilities:Design and...
-
Umeå, Västerbotten, Sweden Umeå University Full timeProject OverviewHigh-throughput DNA sequencing technologies have led to the production of large genome assemblies, including those of conifers, wheat, axolotl salamanders, and giant lungfish. Genome annotation, particularly the identification of transposable elements (TEs), presents a significant challenge in analyzing these large genomes. Deep-learning...
-
PhD Position in Medical Science
3 weeks ago
Umeå, Västerbotten, Sweden Umeå University Full timePhD Position in Medical ScienceWe are seeking a highly motivated and qualified candidate to join our research team as a PhD student in Medical Science with a focus on Neurophysiology. The successful candidate will have the opportunity to contribute to cutting-edge research in the field of sensorimotor neurophysiology and work closely with our team of...
-
Umeå, Västerbotten, Sweden Umeå University Full timeResearch Opportunity at Umeå UniversityThe Department of Applied Physics and Electronics at Umeå University is seeking a PhD student to join their research group "Cooperative and Intelligent Embedded Systems". The successful candidate will work on safe and secure intelligent embedded systems, contributing to the development of innovative solutions in...
-
PhD Researcher in Neurophysiology
1 week ago
Umeå, Västerbotten, Sweden Umeå University Full timePhD Research Position in NeurophysiologyWe are seeking a highly motivated PhD researcher to join our team at the Department of Medical and Translational Biology at Umeå University. The successful candidate will have the opportunity to work on a PhD project in neurophysiology, focusing on sensorimotor control and proprioception.Description of the PhD...
-
Umeå, Västerbotten, Sweden Umeå University Full timeWe are seeking a highly motivated PhD student to join our dynamic research environment at the Department of Molecular Biology at Umeå University.The successful applicant will develop a research project to elucidate the molecular mechanisms controlling malaria parasite development in the mosquito.As part of an international and interdisciplinary...
PhD Position in Mathematics: Geometric Deep Learning at Umeå University
2 months ago
The Department of Mathematics and Mathematical Statistics at Umeå University is seeking a PhD candidate to contribute to the WASP AI program, focusing on geometric deep learning. This four-year position will involve research and third-cycle courses, with the last day to apply being 10 June 2024.
This recruitment is part of a larger expansion of the research group at the department, investigating mathematical foundations of artificial intelligence. The group covers a diverse range of topics in modern machine learning research, including geometric deep learning, non-convex optimization problems, and federated learning.
Project Overview- Deep learning has achieved significant success on complex problems, but the fundamental mathematical understanding of deep learning models remains incomplete. This project aims to address this gap by exploring the mathematical foundations of deep learning, including differential geometry, numerical analysis, and dynamical systems.
- Neural ordinary differential equations (NODEs) represent a recent advance in geometric deep learning, incorporating symmetries and non-Euclidean structures using geometrical principles. NODEs describe the dynamics of information propagating through neural networks in the limit of infinite depth using ordinary differential equations (ODEs) on manifolds.
- The dynamical systems in NODE models are constrained by the intrinsic nature of the dimension of a manifold, fixing the dimension of their state vector. This limitation precludes the use of certain architectural elements, like the encoder-decoder structure used in autoencoders and sequence-to-sequence prediction.
- To remedy these limitations, the project aims to extend NODEs from manifolds to M-polyfolds, a generalization of manifolds where the number of local coordinates is allowed to vary smoothly. This requires the development of a comprehensive geometric framework for flows and integral curves on M-Polyfolds and a theory of group actions compatible with the M-polyfold structure.
The project is part of the AI-Math track within the Wallenberg AI, Autonomous Systems and Software Program (WASP). The PhD student will participate in the WASP graduate school.
For further information and instructions on how to apply, please see the provided link.
