Search Results for author: B. Mehlig

Found 7 papers, 2 papers with code

Finite-time Lyapunov exponents of deep neural networks

no code implementations21 Jun 2023 L. Storm, H. Linander, J. Bec, K. Gustavsson, B. Mehlig

We compute how small input perturbations affect the output of deep neural networks, exploring an analogy between deep networks and dynamical systems, where the growth or decay of local perturbations is characterised by finite-time Lyapunov exponents.

Looking at the posterior: accuracy and uncertainty of neural-network predictions

no code implementations26 Nov 2022 H. Linander, O. Balabanov, H. Yang, B. Mehlig

Here we show that prediction accuracy depends on both epistemic and aleatoric uncertainty in an intricate fashion that cannot be understood in terms of marginalized uncertainty distributions alone.

Active Learning Bayesian Inference +2

Constraints on parameter choices for successful reservoir computing

no code implementations3 Jun 2022 L. Storm, K. Gustavsson, B. Mehlig

By selecting network parameters such that the dynamics of the network is contractive, characterized by a negative maximal Lyapunov exponent, the network may synchronize with the driving signal.

Time Series Time Series Prediction

Improving traffic sign recognition by active search

1 code implementation29 Nov 2021 S. Jaghouar, H. Gustafsson, B. Mehlig, E. Werner, N. Gustafsson

We demonstrate that by sorting the samples of a large, unlabeled set by the estimated probability of belonging to the rare class, we can efficiently identify samples from the rare class.

Active Learning Traffic Sign Recognition

Key parameters for droplet evaporation and mixing at the cloud edge

no code implementations4 Feb 2021 J. Fries, G. Sardina, G. Svensson, B. Mehlig

The distribution of liquid water in ice-free clouds determines their radiative properties, a significant source of uncertainty in weather and climate models.

Fluid Dynamics Atmospheric and Oceanic Physics

Paths to caustic formation in turbulent aerosols

no code implementations15 Dec 2020 Jan Meibohm, Vikash Pandey, Akshay Bhatnagar, Kristian Gustavsson, Dhrubaditya Mitra, Prasad Perlekar, B. Mehlig

The dynamics of small, yet heavy, identical particles in turbulence exhibits singularities, called caustics, that lead to large fluctuations in the spatial particle-number density, and in collision velocities.

Fluid Dynamics

Machine learning with neural networks

1 code implementation17 Jan 2019 B. Mehlig

The material is organised into three parts: Hopfield networks, supervised learning of labeled data, and learning algorithms for unlabeled data sets.

BIG-bench Machine Learning Object Recognition +1

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