Search Results for author: Sven Krippendorf

Found 7 papers, 0 papers with code

Towards a Phenomenological Understanding of Neural Networks: Data

no code implementations1 May 2023 Samuel Tovey, Sven Krippendorf, Konstantin Nikolaou, Christian Holm

This framework is then applied to the problem of optimal data selection for the training of NNs.

A duality connecting neural network and cosmological dynamics

no code implementations22 Feb 2022 Sven Krippendorf, Michael Spannowsky

We demonstrate that the dynamics of neural networks trained with gradient descent and the dynamics of scalar fields in a flat, vacuum energy dominated Universe are structurally profoundly related.

Improving Simulations with Symmetry Control Neural Networks

no code implementations29 Apr 2021 Marc Syvaeri, Sven Krippendorf

The dynamics of physical systems is often constrained to lower dimensional sub-spaces due to the presence of conserved quantities.

Symmetry Control Neural Networks

no code implementations1 Jan 2021 Marc Syvaeri, Sven Krippendorf

We show that such coordinates can be searched for automatically with appropriate loss functions which naturally arise from Hamiltonian dynamics.

Detecting Symmetries with Neural Networks

no code implementations30 Mar 2020 Sven Krippendorf, Marc Syvaeri

Identifying symmetries in data sets is generally difficult, but knowledge about them is crucial for efficient data handling.

Connecting Dualities and Machine Learning

no code implementations12 Feb 2020 Philip Betzler, Sven Krippendorf

Dualities are widely used in quantum field theories and string theory to obtain correlation functions at high accuracy.

BIG-bench Machine Learning

GANs for generating EFT models

no code implementations6 Sep 2018 Harold Erbin, Sven Krippendorf

In this case, the machine knows consistent examples of supersymmetric field theories with a single field and generates new examples of such theories.

Cannot find the paper you are looking for? You can Submit a new open access paper.