Sort by
Refine Your Search
-
Listed
-
Country
-
Employer
- Heriot Watt University
- Technical University of Denmark
- Aarhus University
- CEA
- Georgetown University
- King Abdullah University of Science and Technology
- Nature Careers
- Purdue University
- Radboud University
- Rutgers University
- SciLifeLab
- Swedish University of Agricultural Sciences
- The University of Arizona
- University of Adelaide
- University of Copenhagen
- University of Idaho
- University of London
- University of Luxembourg
- University of Minnesota
- University of Oslo
- University of Virginia
- 11 more »
- « less
-
Field
-
project on Bayesian comparisons between artificial and natural representations to improve our understanding how natural and artificial intelligences process information. The project is led by Heiko Schütt
-
projects ranging from score-based generative models, energy-based models, Bayesian analysis of graph and network structured data, highly multivariate stochastic processes; with data applications ranging from
-
experiments. The objective is to develop Bayesian causal models and neural networks capable of identifying relevant causal relationships between instrumental parameters and observed anomalies. The work will
-
-traditional, e.g., event data) and network structures (for sensor networks). In this project, we will investigate Bayesian deep learning approaches to training models under uncertainty for several sensing
-
theoretical understanding of statistical machine learning methods relevant to the project: Bayesian learning, machine learning, spiking neural networks. Experience of programming (e.g. with Python) and data
-
focused on understanding and countering harmful narratives and, mis/disinformation, and applying social network analysis. To be successful you will need: PhD in a relevant discipline such as computer
-
regressions, Bayesian analyses). You preferably have experience supervising and/or teaching students. You preferably have knowledge of swarm robotics and/or deep learning artificial neural networks (e.g. CNN
-
development. Experience with implementing statistical learning or machine learning (e.g. Bayesian inference, deep-learning). Programming skills in Python and experience with frameworks like PyTorch, Keras, Pyro
-
fresh perspective on how specialized brain networks can identify and categorize causes of sensory inputs, integrate information with other networks, and adapt to new stimuli. It proposes that perception
-
related to gravitational wave astronomy. The primary aim will be the development of advanced approaches for computational Bayesian Inference to measure the properties of Compact Binary Coalescence signals