Estimator Meets Equilibrium Perspective: A Rectified Straight Through Estimator for Binary Neural Networks Training.
Xiao-Ming WuDian ZhengZuhao LiuWei-Shi ZhengPublished in: CoRR (2023)
Keyphrases
- neural network
- least squares
- maximum likelihood
- training process
- training algorithm
- pattern recognition
- training set
- maximum a posteriori
- self organizing maps
- variance estimator
- backpropagation algorithm
- importance sampling
- genetic algorithm
- fuzzy logic
- viewpoint
- recurrent networks
- back propagation
- training phase
- hamming distance
- machine learning
- variance reduction
- decision trees
- feedforward neural networks
- feed forward neural networks
- reinforcement learning
- artificial neural networks
- estimation error
- multilayer perceptron
- straight line
- test set