2019 · 21 citations · 24 references
ComputingComputer ScienceEdge ComputingMachine LearningOptimizationDeep LearningDimensionality ReductionEdge DevicesNeural NetworksOptimization For Machine LearningPattern RecognitionEdge Machine LearningNeural Network ModelingNeural Network QuantizationOptimization AlgorithmsPrecisionPrecision LossQuantizationSimulation-based Loss Analysis
This paper focuses on convolution neural network quantization problem. The quantization has a distinct stage of data conversion from floating-point into integer-point numbers. In general, the process of quantization is associated with the reduction of the matrix dimension via limited precision of the numbers. However, the training and inference stages of deep learning neural network are limited by the space of the memory and a variety of factors including programming complexity and even reliability of the system. On the whole the process of quantization becomes more and more popular due to significant impact on performance and minimal accuracy loss. Various techniques for networks quantization have been already proposed, including quantization aware training and integer arithmetic-only inference. Yet, a detailed comparison of various quantization configurations, combining all proposed methods haven't been presented yet. This comparison is important to understand selection of quantization hyperparameters during training to optimize networks for inference while preserving their robustness. In this work, we perform in-depth analysis of parameters in the quantization aware training, the process of simulating precision loss in the forward pass by quantizing and dequantizing tensors. Specifically, we modify rounding modes, input preprocessing, output data signedness, bitwidth of the quantization and locations of precision loss simulation to evaluate how they affect accuracy of deep neural network aimed at performing efficient calculations on resource-constrained devices.
24
Deep Residual Learning for Image Recognition
Kaiming He, Xiangyu Zhang, Shaoqing Ren et al. · 2016 · 222.1K citations · Full text
MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applications
Andrew Howard, Menglong Zhu, Bo Chen et al. · arXiv (Cornell University) · 2017 · 9.9K citations · Full text
Deep Learning with Limited Numerical Precision
Suyog Gupta, Ankur Agrawal, Kailash Gopalakrishnan et al. · arXiv (Cornell University) · 2015 · 1.1K citations · Full text
Pedro López, Alberto Montresor, Dick Epema et al. · ACM SIGCOMM Computer Communication Review · 2015 · 932 citations · Full text