Zobrazeno 1 - 10
of 26
pro vyhledávání: '"Hihn, Heinke"'
Autor:
Hihn, Heinke, Braun, Daniel A.
One notable weakness of current machine learning algorithms is the poor ability of models to solve new problems without forgetting previously acquired knowledge. The Continual Learning paradigm has emerged as a protocol to systematically investigate
Externí odkaz:
http://arxiv.org/abs/2211.07725
Autor:
Hihn, Heinke, Braun, Daniel A.
One weakness of machine learning algorithms is the poor ability of models to solve new problems without forgetting previously acquired knowledge. The Continual Learning (CL) paradigm has emerged as a protocol to systematically investigate settings wh
Externí odkaz:
http://arxiv.org/abs/2110.12667
In many real-world pattern recognition scenarios, such as in medical applications, the corresponding classification tasks can be of an imbalanced nature. In the current study, we focus on binary, imbalanced classification tasks, i.e.~binary classific
Externí odkaz:
http://arxiv.org/abs/2011.14764
Autor:
Hihn, Heinke, Braun, Daniel A.
Publikováno v:
Neural Processing Letters, 1-34, 2020
Joining multiple decision-makers together is a powerful way to obtain more sophisticated decision-making systems, but requires to address the questions of division of labor and specialization. We investigate in how far information constraints in hier
Externí odkaz:
http://arxiv.org/abs/2011.01845
Autor:
Hihn, Heinke, Braun, Daniel A.
The goal of meta-learning is to train a model on a variety of learning tasks, such that it can adapt to new problems within only a few iterations. Here we propose a principled information-theoretic model that optimally partitions the underlying probl
Externí odkaz:
http://arxiv.org/abs/1911.00348
Information-theoretic bounded rationality describes utility-optimizing decision-makers whose limited information-processing capabilities are formalized by information constraints. One of the consequences of bounded rationality is that resource-limite
Externí odkaz:
http://arxiv.org/abs/1907.11452
Publikováno v:
Pancioni L., Schwenker F., Trentin E. (eds) Artificial Neural Networks in Pattern Recognition. ANNPR 2018. Lecture Notes in Computer Science, vol 11081. Springer, Cham
Bounded rationality investigates utility-optimizing decision-makers with limited information-processing power. In particular, information theoretic bounded rationality models formalize resource constraints abstractly in terms of relative Shannon info
Externí odkaz:
http://arxiv.org/abs/1809.01575
Autor:
Hihn, Heinke, Braun, Daniel A.
Publikováno v:
ICLR Workshop on Agent Learning in Open-Endedness
One weakness of machine learning algorithms is the poor ability of models to solve new problems without forgetting previously acquired knowledge. The Continual Learning (CL) paradigm has emerged as a protocol to systematically investigate settings wh
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::c7e88ce4f183d476556a8a4ca4e80330
Autor:
Hihn, Heinke, Braun, Daniel A.
Publikováno v:
Machine Learning; Feb2023, Vol. 112 Issue 2, p655-686, 32p