530 citations · 565 across the 10 of their papers we have counts for
10 papers
IO Factory: Simulating AI-Enabled Influence Campaigns at Scale
Lukasz Olejnik, Wenchao Dong, Jonas R. Kunst +4
We introduce IO Factory, an AI-driven framework for simulating information and influence campaigns as fully integrated, traceable processes. The threat of digital manipulation now…
Unreliable Uncertainty Estimates with Monte Carlo Dropout
Aslak Djupskås, Alexander Johannes Stasik, Signe Riemer-Sørensen
Reliable uncertainty estimation is crucial for machine learning models, especially in safety-critical domains. While exact Bayesian inference offers a principled approach, it is of…
Examining the robustness of Physics-Informed Neural Networks to noise for Inverse Problems
Aleksandra Jekic, Afroditi Natsaridou, Signe Riemer-Sørensen +2
Approximating solutions to partial differential equations (PDEs) is fundamental for the modeling of dynamical systems in science and engineering. Physics-informed neural networks (…
Road Graph Generator: Mapping roads at construction sites from GPS data
Katarzyna Michałowska, Helga Margrete Bodahl Holmestad, Signe Riemer-Sørensen
We propose a new method for inferring roads from GPS trajectories to map construction sites. This task presents a unique challenge due to the erratic and non-standard movement patt…
Machine Learning based Pointing Models for Radio/Sub-millimeter Telescopes
Bendik Nyheim, Signe Riemer-Sørensen, Rodrigo Parra +1
Radio, sub-millimeter and millimeter ground-based telescopes are powerful instruments for studying the gas and dust-rich regions of the Universe that are invisible at optical wavel…
DON-LSTM: Multi-Resolution Learning with DeepONets and Long Short-Term Memory Neural Networks
Katarzyna Michałowska, Somdatta Goswami, George Em Karniadakis +1
Deep operator networks (DeepONets, DONs) offer a distinct advantage over traditional neural networks in their ability to be trained on multi-resolution data. This property becomes…
Neural Operator Learning for Long-Time Integration in Dynamical Systems with Recurrent Neural Networks
Katarzyna Michałowska, Somdatta Goswami, George Em Karniadakis +1
Deep neural networks are an attractive alternative for simulating complex dynamical systems, as in comparison to traditional scientific computing methods, they offer reduced comput…
Deep Reinforcement Learning for Long Term Hydropower Production Scheduling
Signe Riemer-Sorensen, Gjert H. Rosenlund
We explore the use of deep reinforcement learning to provide strategies for long term scheduling of hydropower production. We consider a use-case where the aim is to optimise the y…
A gradient boosting approach for optimal selection of bidding strategies in reservoir hydro
Hans Ole Riddervold, Signe Riemer-Sørensen, Peter Szederjesi +1
Power producers use a wide range of decision support systems to manage and plan for sales in the day-ahead electricity market, and they are often faced with the challenge of choosi…
Beyond CDM: Problems, solutions, and the road ahead
Philip Bull, Yashar Akrami, Julian Adamek +37
Despite its continued observational successes, there is a persistent (and growing) interest in extending cosmology beyond the standard model, CDM. This is motivated by a range o…