Binarized neural network neuron threshold tests and last-layer scores can be equivalently expressed as Sugeno integrals on binary inputs, yielding explicit set-function and rule-based representations.
Towards a reconciliation between reasoning and learning-a position paper
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
-
A Sugeno Integral View of Binarized Neural Network Inference
Binarized neural network neuron threshold tests and last-layer scores can be equivalently expressed as Sugeno integrals on binary inputs, yielding explicit set-function and rule-based representations.