An Empirical study of Binary Neural Networks' Optimisation

96 citations recorded by the source corpus.

How researchers see this paper

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

Network Pruning via Transformable Architecture Search (2019, methodology): “mputation costs for all candidate networks, where the weight is the sampling probability. F cost(A) indicates the actual cost of the searched architecture, whose width and depth are derived from A. t2[0;1] denotes a toleration ratio, which slows down Algorithm 1 The TAS Procedure Input: split the tr”
A Survey of Quantization Methods for Efficient Neural Network Inference (2021, neutral): “…models has also been shown as a promising method to recover the accuracy degradation after binarization/ternarization [33, 173, 189, 252]. c) Improved Training Method: Another interesting branch of work aims for better training methods for binary/ternary models [5, 20, 44, 73, 157, 160, 276, 279].”
Reducing the Computational Cost of Deep Generative Models with Binary Neural Networks (2020, methodology): “Taking a trained model with real-valued weights and binarizing the weights has been shown to be lead to significant worsening of performance (Alizadeh et al., 2019).”
ReActNet: Towards Precise Binary Neural Network with Generalized Activation Functions (2020, background): “In addition to architectural design, studies on 1-bit CNNs expand from training algorithms [34,1,44,3] and binary optimizer design [13], to better approximation of binary weights and activations [28,11,35].”