no code implementations • 21 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.
no code implementations • 26 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.
no code implementations • 3 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.
1 code implementation • 29 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.
no code implementations • 4 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
no code implementations • 15 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
1 code implementation • 17 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.