用于逻辑门控残差神经网络的直方图均衡化量化
Histogram-Equalized Quantization for logic-gated Residual Neural Networks
AI总结:
本文提出自适应线性对称量化框架HEQ,通过步长优化自动调整阈值,在CIFAR-10达到先进性能,并支持低硬件复杂度、高精度的逻辑门控残差网络训练。
摘要:
在量化神经网络中,根据数据或模型损失调整量化似乎是实现高精度的必要条件。本工作提出直方图均衡化量化(HEQ),这是一种用于线性对称量化的自适应框架。HEQ通过独特的步长优化自动调整量化阈值。我们通过实验表明,HEQ在CIFAR-10上取得了最先进的性能。在STL-10数据集上的实验甚至表明,HEQ能够恰当训练我们提出的逻辑门控(OR、MUX)残差网络,并以低于以往工作的硬件复杂度实现更高精度。
英文摘要:
Adjusting the quantization according to the data or to the model loss seems mandatory to enable a high accuracy in the context of quantized neural networks. This work presents Histogram-Equalized Quantization (HEQ), an adaptive framework for linear symmetric quantization. HEQ automatically adapts the quantization thresholds using a unique step size optimization. We empirically show that HEQ achieves state-of-the-art performances on CIFAR-10. Experiments on the STL-10 dataset even show that HEQ enables a proper training of our proposed logic-gated (OR, MUX) residual networks with a higher accuracy at a lower hardware complexity than previous work.
机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。