266 citations · 505 across the 37 of their papers we have counts for
38 papers
Interpreting Neural Networks through the Polytope Lens
Sid Black, Lee Sharkey, Leo Grinsztajn +8
Mechanistic interpretability aims to explain what a neural network has learned at a nuts-and-bolts level. What are the fundamental primitives of neural network representations? Pre…
Hierarchically Structured Task-Agnostic Continual Learning
Heinke Hihn, Daniel A. Braun
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 Lear…
Thermodynamic fluctuation theorems govern human sensorimotor learning
Pedro Hack, Cecilia Lindig-Leon, Sebastian Gottwald +1
The application of thermodynamic reasoning in the study of learning systems has a long tradition. Recently, new tools relating perfect thermodynamic adaptation to the adaptation pr…
Countability constraints in order-theoretic approaches to computability
Pedro Hack, Daniel A. Braun, Sebastian Gottwald
Computability on uncountable sets has no standard formalization, unlike that on countable sets, which is given by Turing machines. Some of the approaches to define computability in…
Computation as uncertainty reduction: a simplified order-theoretic framework
Pedro Hack, Daniel A. Braun, Sebastian Gottwald
Although there is a somewhat standard formalization of computability on countable sets given by Turing machines, the same cannot be said about uncountable sets. Among the approache…
The infinite information gap between mathematical and physical representations
Pedro Hack, Daniel A. Braun, Sebastian Gottwald
Partial orders have been used to model several experimental setups, going from classical thermodynamics and general relativity to the quantum realm with its resource theories. In o…