AdaSTE: An Adaptive Straight-Through Estimator to Train Binary Neural Networks.
Huu LeRasmus Kjær HøierChe-Tsung LinChristopher ZachPublished in: CoRR (2021)
Keyphrases
- neural network
- fuzzy logic
- least squares
- pattern recognition
- maximum likelihood
- genetic algorithm
- artificial neural networks
- back propagation
- neural network model
- non binary
- maximum a posteriori
- feed forward
- line segments
- fuzzy systems
- multi layer
- multilayer perceptron
- neural nets
- data sets
- self organizing maps
- learning rules
- machine learning
- hopfield neural network
- variance estimator