Browsing Department of Informatics by Journals "Proceedings of the Northern Lights Deep Learning Workshop"

Now showing items 1-4 of 4

    • A contrastive learning approach for individual re-identification in a wild fish population 

      Olsen, Ørjan Langøy; Sørdalen, Tonje Knutsen; Goodwin, Morten; Malde, Ketil; Knausgård, Kristian Muri; Halvorsen, Kim Aleksander Tallaksen (Journal article; Peer reviewed, 2023)
      In both terrestrial and marine ecology, physical tagging is a frequently used method to study population dynamics and behavior. However, such tagging techniques are increasingly being replaced by individual re-identification ...

    • Extracting Rules from Neural Networks with Partial Interpretations 

      Persia, Cosimo Damiano; Ozaki, Ana (Journal article; Peer reviewed, 2022)
      We investigate the problem of extracting rules, expressed in Horn logic, from neural network models. Our work is based on the exact learning model, in which a learner interacts with a teacher (the neural network model) via ...

    • An Inductive Bias for Emergent Communication in a Continuous Setting 

      Villanger, John Isak Fjellvang; Bojesen, Troels Arnfred (Journal article; Peer reviewed, 2024)
      We study emergent communication in a multi-agent reinforcement learning setting, where the agents solve cooperative tasks and have access to a communication channel. The communication channel may consist of either discrete ...

    • Measuring Adversarial Robustness using a Voronoi-Epsilon Adversary 

      Kim, Hyeongji; Parviainen, Pekka; Malde, Ketil (Journal article; Peer reviewed, 2023)
      Previous studies on robustness have argued that there is a tradeoff between accuracy and adversarial accuracy. The tradeoff can be inevitable even when we neglect generalization. We argue that the tradeoff is inherent to ...