Harder classification tasks produce neural representations whose accuracy collapses under binarization and shuffling while easier tasks remain robust, defining task complexity via the performance gap between full-precision and perturbed networks.
Title resolution pending
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
verdicts
UNVERDICTED 2representative citing papers
A novel node-partitioning lumping scheme reduces arbitrary epidemic models on networks to approximate Markov Population Models with smaller state spaces.
citing papers explorer
-
Task complexity shapes internal representations and robustness in neural networks
Harder classification tasks produce neural representations whose accuracy collapses under binarization and shuffling while easier tasks remain robust, defining task complexity via the performance gap between full-precision and perturbed networks.
-
Reducing Spreading Processes on Networks to Markov Population Models
A novel node-partitioning lumping scheme reduces arbitrary epidemic models on networks to approximate Markov Population Models with smaller state spaces.