3 papers
math.DS2026
Universal Analog Computation: Fraïssé Limits of Dynamical Systems
Levin Hornischer
Analog computation is an alternative to digital computation, that has recently re-gained prominence, since it includes neural networks and neuromorphic computing. Further important…
cs.AI2025
Learning How to Vote with Principles: Axiomatic Insights Into the Collective Decisions of Neural Networks
Levin Hornischer, Zoi Terzopoulou
Can neural networks be applied in voting theory, while satisfying the need for transparency in collective decisions? We propose axiomatic deep voting: a framework to build and eval…
cs.LG2025
Explaining Neural Networks with Reasons
Levin Hornischer, Hannes Leitgeb
We propose a new interpretability method for neural networks, which is based on a novel mathematico-philosophical theory of reasons. Our method computes a vector for each neuron, c…