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.
Binary neural networks: A survey.Pattern Recognition, 105:107281
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
citation-role summary
background 1
citation-polarity summary
years
2026 2verdicts
UNVERDICTED 2roles
background 1polarities
background 1representative citing papers
HTAF is a sigmoid-tanh composite that approximates the Heaviside function to allow stable gradient training of binary activation networks, yielding ICBMs with stable discretization and competitive performance on image tasks.
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.
-
A Composite Activation Function for Learning Stable Binary Representations
HTAF is a sigmoid-tanh composite that approximates the Heaviside function to allow stable gradient training of binary activation networks, yielding ICBMs with stable discretization and competitive performance on image tasks.