Zobrazeno 1 - 7
of 7
pro vyhledávání: '"Löwe, Mathias"'
Autor:
Lafargue, Raphael, Smith, Luke, Vermet, Franck, Löwe, Mathias, Reid, Ian, Gripon, Vincent, Valmadre, Jack
The predominant method for computing confidence intervals (CI) in few-shot learning (FSL) is based on sampling the tasks with replacement, i.e.\ allowing the same samples to appear in multiple tasks. This makes the CI misleading in that it takes into
Externí odkaz:
http://arxiv.org/abs/2409.02850
Dealing with Adversarial Player Strategies in the Neural Network Game iNNk through Ensemble Learning
Autor:
Löwe, Mathias, Villareale, Jennifer, Freed, Evan, Sladek, Aleksanteri, Zhu, Jichen, Risi, Sebastian
Applying neural network (NN) methods in games can lead to various new and exciting game dynamics not previously possible. However, they also lead to new challenges such as the lack of large, clean datasets, varying player skill levels, and changing g
Externí odkaz:
http://arxiv.org/abs/2107.02052
We introduce a novel combination of Bayesian Models (BMs) and Neural Networks (NNs) for making predictions with a minimum expected risk. Our approach combines the best of both worlds, the data efficiency and interpretability of a BM with the speed of
Externí odkaz:
http://arxiv.org/abs/2103.15682
Autor:
Zhu, Jichen, Villareale, Jennifer, Javvaji, Nithesh, Risi, Sebastian, Löwe, Mathias, Weigelt, Rush, Harteveld, Casper
The advent of artificial intelligence (AI) and machine learning (ML) bring human-AI interaction to the forefront of HCI research. This paper argues that games are an ideal domain for studying and experimenting with how humans interact with AI. Throug
Externí odkaz:
http://arxiv.org/abs/2101.06220
Autor:
Villareale, Jennifer, Acosta-Ruiz, Ana, Arcaro, Samuel, Fox, Thomas, Freed, Evan, Gray, Robert, Löwe, Mathias, Nuchprayoon, Panote, Sladek, Aleksanteri, Weigelt, Rush, Li, Yifu, Risi, Sebastian, Zhu, Jichen
This paper presents iNNK, a multiplayer drawing game where human players team up against an NN. The players need to successfully communicate a secret code word to each other through drawings, without being deciphered by the NN. With this game, we aim
Externí odkaz:
http://arxiv.org/abs/2007.09177
Autor:
Löwe, Mathias
Publikováno v:
Löwe, M 2021, Towards Improved Marketing Mix Decisions through Deep Learning and Human-AI Collaboration . ITU-DS, no. 189, IT-Universitetet i København .
With the recent boom in machine learning (ML), people are interacting with a growing number of ML-advised products in many aspects of their everyday life. However, the underlying logic in the decision-making process of ML systems generally lacks tran
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=od______2988::2ac63a69d552dae801713de95cf5c2f5
https://pure.itu.dk/portal/da/publications/6751170a-5ecb-4318-8ac3-34dafb6098f8
https://pure.itu.dk/portal/da/publications/6751170a-5ecb-4318-8ac3-34dafb6098f8
Autor:
Blamberger, Günter, Vosskamp, Wilhelm, Motzkin, Gabriel, Balke, Friedrich, Löwe, Mathias, Schmitt, Arbogast, Berghahn, Klaus L., Liska, Vivian, Roussel, Martin, Seeber, Hans Ulrich, Leiss, Judith, Maeda, Ryozo, Simanowski, Roberto, Fohrmann, Jürgen, Bohrer, Karl Heinz
Utopien denken Möglichkeiten von Zukunft. Mit Beginn der historischen Moderne, in der die Erwartung an die Zukunft die Erfahrung der Vergangenheit übersteigt, entstehen in der je aktuellen Gegenwart Entwürfe, die Utopien genannt werden können. Di
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=od_______199::bec27c9b1a8cafb2aca4b6259fae1967
https://kups.ub.uni-koeln.de/7945/
https://kups.ub.uni-koeln.de/7945/