A complete classification of symmetries in shallow ReLU networks is achieved by using the non-differentiability of ReLU.
For neural networks, function determines form
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
A Complete Symmetry Classification of Shallow ReLU Networks
A complete classification of symmetries in shallow ReLU networks is achieved by using the non-differentiability of ReLU.