Sort by
Refine Your Search
-
learning problems involving a-priori known symmetries. A simple example are convolutional neural networks, that are known to be invariant towards translations. Using representation theory, one can build
-
. Machine learning: experience with algorithms such as nearest-neighbor, simplex projection, recurrent neural networks, singular value decomposition and/or autoencoders; experience in frameworks like
-
on knowledge graphs and graph neural networks. Health data is indefinitely siloed, split across various systems and formats, using different ontologies, making it challenging to integrate, harmonize, and analyze
-
of machine learning or statistical models to biological data. Graph-theoretic modeling of neural or behavioral networks. Neural population dynamics and dimensionality reduction techniques. Development
-
experience with machine learning techniques in general and neural networks in particular will be highly beneficial.
-
improve predictive modelling for CVD. We pay particular attention to methods driven by generative diffusion models, physics-informed neural networks, and probabilistic numerics. As postdoc, you will
-
stochastic constraints, Implicit regularization in neural networks, Optimization with quantum computation, Distributed optimization and federated learning, Operator splitting methods in optimization, Continual
-
stochastic constraints, Implicit regularization in neural networks, Optimization with quantum computation, Distributed optimization and federated learning, Operator splitting methods in optimization, Continual
-
conditions and in various disease states. Research projects include a broad range of studies on the molecular and cellular levels, networks of neurons, and the organization of the nervous system as a whole