131 citations · 241 across the 17 of their papers we have counts for
18 papers
Soft Geometric Inductive Bias for Object Centric Dynamics
Hampus Linander, Conor Heins, Alexander Tschantz +2
Physical systems are naturally parameterized in terms of geometric entities and their transformations. While exact equivariance can be a powerful inductive bias, real-world applica…
AXIOM: Learning to Play Games in Minutes with Expanding Object-Centric Models
Conor Heins, Toon Van de Maele, Alexander Tschantz +11
Current deep reinforcement learning (DRL) approaches achieve state-of-the-art performance in various domains, but struggle with data efficiency compared to human learning, which le…
PEAR: Equal Area Weather Forecasting on the Sphere
Hampus Linander, Tage Tykesson, Pietro Rosso +3
Artificial intelligence is rapidly reshaping the natural sciences, with weather forecasting emerging as a flagship AI4Science application where machine learning models can now riva…
Bayesian Predictive Coding
Alexander Tschantz, Magnus Koudahl, Hampus Linander +4
Predictive coding (PC) is an influential theory of information processing in the brain, providing a biologically plausible alternative to backpropagation. It is motivated in terms…
Learning Chern Numbers of Topological Insulators with Gauge Equivariant Neural Networks
Longde Huang, Oleksandr Balabanov, Hampus Linander +3
Equivariant network architectures are a well-established tool for predicting invariant or equivariant quantities. However, almost all learning problems considered in this context f…
Uncertainty quantification in fine-tuned LLMs using LoRA ensembles
Oleksandr Balabanov, Hampus Linander
Fine-tuning large language models can improve task specific performance, although a general understanding of what the fine-tuned model has learned, forgotten and how to trust its p…
HEAL-SWIN: A Vision Transformer On The Sphere
Oscar Carlsson, Jan E. Gerken, Hampus Linander +4
High-resolution wide-angle fisheye images are becoming more and more important for robotics applications such as autonomous driving. However, using ordinary convolutional neural ne…
Finite-time Lyapunov exponents of deep neural networks
L. Storm, H. Linander, J. Bec +2
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 l…
Bayesian posterior approximation with stochastic ensembles
Oleksandr Balabanov, Bernhard Mehlig, Hampus Linander
We introduce ensembles of stochastic neural networks to approximate the Bayesian posterior, combining stochastic methods such as dropout with deep ensembles. The stochastic ensembl…
Looking at the posterior: accuracy and uncertainty of neural-network predictions
H. Linander, O. Balabanov, H. Yang +1
Bayesian inference can quantify uncertainty in the predictions of neural networks using posterior distributions for model parameters and network output. By looking at these posteri…
Real-time semantic segmentation on FPGAs for autonomous vehicles with hls4ml
Nicolò Ghielmetti, Vladimir Loncar, Maurizio Pierini +8
In this paper, we investigate how field programmable gate arrays can serve as hardware accelerators for real-time semantic segmentation tasks relevant for autonomous driving. Consi…
Equivariance versus Augmentation for Spherical Images
Jan E. Gerken, Oscar Carlsson, Hampus Linander +3
We analyze the role of rotational equivariance in convolutional neural networks (CNNs) applied to spherical images. We compare the performance of the group equivariant networks kno…
Geometric Deep Learning and Equivariant Neural Networks
Jan E. Gerken, Jimmy Aronsson, Oscar Carlsson +4
We survey the mathematical foundations of geometric deep learning, focusing on group equivariant and gauge equivariant neural networks. We develop gauge equivariant convolutional n…
Fast convolutional neural networks on FPGAs with hls4ml
Thea Aarrestad, Vladimir Loncar, Nicolò Ghielmetti +17
We introduce an automated tool for deploying ultra low-latency, low-power deep neural networks with convolutional layers on FPGAs. By extending the hls4ml library, we demonstrate a…
The non-linear coupled spin 2 - spin 3 Cotton equation in three dimensions
Hampus Linander, Bengt E. W. Nilsson
In the context of three-dimensional conformal higher spin theory we derive, in the frame field formulation, the full non-linear spin 3 Cotton equation coupled to spin 2. This is do…
Off-shell structure of twisted (2,0) theory
Ulf Gran, Hampus Linander, Bengt E. W. Nilsson
A -exact off-shell action is constructed for twisted abelian (2,0) theory on a Lorentzian six-manifold of the form , where is a flat two-manifold and…
The trouble with twisting (2,0) theory
Louise Anderson, Hampus Linander
We consider a twisted version of the abelian theory placed upon a Lorenzian six-manifold with a product structure, . This is done by an investigation of…
(2,0) theory on circle fibrations
Hampus Linander, Fredrik Ohlsson
We consider (2,0) theory on a manifold M_6 that is a fibration of a spatial S^1 over some five-dimensional base manifold M_5. Initially, we study the free (2,0) tensor multiplet wh…