Reduction of Quantizing Noise by Use of Feedback

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

Quantized Neural Networks: Training Neural Networks with Low Precision Weights and Activations (2016, methodology): “The binarization noise is independent between diﬀerent weights, either by construction (by using stochastic quantization) or by assumption (a common simpliﬁcation; see Spang and Schultheiss, 1962).”