Standard CNN pipeline is a cross-lattice non-idempotent operator; three idempotent morphological layer designs are characterized using lattice adjunctions.
Neural networks with hybrid morphological/rank/linear nodes: a unifying framework with applications to handwritten character recognition,
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.AI 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Lattice theory and algebraic models for deep convolutional learning based on mathematical morphology
Standard CNN pipeline is a cross-lattice non-idempotent operator; three idempotent morphological layer designs are characterized using lattice adjunctions.