The two kinds of free energy and the Bayesian revolution

S Gottwald, DA Braun - PLoS computational biology, 2020 - journals.plos.org
The concept of free energy has its origins in 19th century thermodynamics, but has recently
found its way into the behavioral and neural sciences, where it has been promoted for its …

Bounded rational decision-making from elementary computations that reduce uncertainty

S Gottwald, DA Braun - Entropy, 2019 - mdpi.com
In its most basic form, decision-making can be viewed as a computational process that
progressively eliminates alternatives, thereby reducing uncertainty. Such processes are …

Specialization in hierarchical learning systems: a unified information-theoretic approach for supervised, unsupervised and reinforcement learning

H Hihn, DA Braun - Neural Processing Letters, 2020 - Springer
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 …

An information-theoretic on-line learning principle for specialization in hierarchical decision-making systems

H Hihn, S Gottwald, DA Braun - 2019 IEEE 58th conference on …, 2019 - ieeexplore.ieee.org
Information-theoretic bounded rationality describes utility-optimizing decision-makers whose
limited information-processing capabilities are formalized by information constraints. One of …

Bounded Rational Decision Networks With Belief Propagation

G Schmid, S Gottwald, DA Braun - Neural Computation, 2024 - direct.mit.edu
Complex information processing systems that are capable of a wide variety of tasks, such as
the human brain, are composed of specialized units that collaborate and communicate with …