Showing 2025Show all
3 papers · 1 filter
cs.IT2025
What should a neuron aim for? Designing local objective functions based on information theory
Andreas C. Schneider, Valentin Neuhaus, David A. Ehrlich +4
In modern deep neural networks, the learning dynamics of the individual neurons is often obscure, as the networks are trained via global optimization. Conversely, biological system…
q-bio.NC2025
Learning to cluster neuronal function
Nina S. Nellen, Polina Turishcheva, Michaela VystrÄilová +4
Deep neural networks trained to predict neural activity from visual input and behaviour have shown great potential to serve as digital twins of the visual cortex. Per-neuron embedd…
stat.ML2025
Hierarchical clustering with maximum density paths and mixture models
Martin Ritzert, Polina Turishcheva, Laura Hansel +3
Hierarchical clustering is an effective, interpretable method for analyzing structure in data. It reveals insights at multiple scales without requiring a predefined number of clust…