by Tove Kvarnström | Feb 28, 2023
PI: Elina Rönnberg (LiU); co-PI: Susanna F. de Rezende (LU) Improved methods for solving discrete optimisation problems have a great potential to contribute to sustainability and energy efficiency, as well as to trustworthiness of systems. The goal of this project is...
by Tove Kvarnström | Feb 28, 2023
PI: Oscar Gustafsson (LiU); co-PI: Joachim Rodrigues (LU) Trading energy for accuracy is a promising approach to reduce the computing energy dissipation. Especially, for classes of applications with inherent resiliency, including AI/ML, significant reductions can be...
by Lena Tasse | May 3, 2021
PI: Pontus Giselsson (LU). Generative adversarial networks (GANs) are generative networks designed to learn probability distributions of training data. They consist of two deep neural networks with opposite objectives. One network, the generator, generates new fake...
by Lena Tasse | May 3, 2021
PI: Marco Kuhlmann (LiU). Collaborators: Pierre Nugues (LU); iMatrics AB (Linköping). The field of natural language processing (NLP) has seen major progress during the last few years with the development of deep neural language models, which learn tasks such as...
by Lena Tasse | May 3, 2021
PI: Fredrik Heintz (LiU) A major open research challenge is developing privacy-preserving machine learning methods that both achieves high performance and privacy guarantees even though the original training data contains sensitive personal information. The...
