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.
hub
Title resolution pending
2 Pith papers cite this work, alongside 5,353 external citations. Polarity classification is still indexing.
2
Pith papers citing it
5,353
external citations · OpenAlex
hub tools
verdicts
UNVERDICTED 2representative citing papers
A crossing activation function combined with virtual noise fields allows one neural network to learn multiple functions assigned to different noise locations, with capacity rising when noise arrangement matches function proximity.
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.
-
Spatial Partial Functionalization of Neural Networks based on Noise Fields
A crossing activation function combined with virtual noise fields allows one neural network to learn multiple functions assigned to different noise locations, with capacity rising when noise arrangement matches function proximity.