ReLU networks' division of input space into convex polytopal regions permits direct extraction of causal rules that exactly match the original network's linear behavior in each region.
Title resolution pending
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
years
2026 2verdicts
UNVERDICTED 2representative citing papers
Continual learning robots form a significantly more stable invariant subnetwork than constant-task controls, and preserving it improves adaptation while damaging it hurts performance.
citing papers explorer
-
Causal Explanations from the Geometric Properties of ReLU Neural Networks
ReLU networks' division of input space into convex polytopal regions permits direct extraction of causal rules that exactly match the original network's linear behavior in each region.
-
Evidence of an Emergent "Self" in Continual Robot Learning
Continual learning robots form a significantly more stable invariant subnetwork than constant-task controls, and preserving it improves adaptation while damaging it hurts performance.