无需重训练，用近似乘法器降低深度网络推理误差，省电45%。
Leveraging Highly Approximated Multipliers in DNN Inference
- 引入控制变量近似技术，减少近似乘法带来的误差。
- 相比精确设计，功耗降低45%，平均精度损失小于1%。
- 适合对能效敏感且需高精度的深度神经网络部署场景。
本文提出一种控制变量近似技术，可充分利用深度神经网络（DNN）加速器中的高度近似乘法器。该方法无需重新训练，显著降低近似乘法引入的误差，提升整体推理精度。实验结果表明，在六种不同DNN和多种近似乘法器上，相比精确设计，本方法实现相同性能、45%的功耗降低，平均精度损失低于1%；相比未使用本技术的近似设计，精度平均提升1.9倍。
原文摘要 · Abstract (English)
In this work, we present a control variate approximation technique that enables the exploitation of highly approximate multipliers in Deep Neural Network (DNN) accelerators. Our approach does not require retraining and significantly decreases the induced error due to approximate multiplications, improving the overall inference accuracy. As a result, our approach enables satisfying tight accuracy loss constraints while boosting the power savings. Our experimental evaluation, across six different DNNs and several approximate multipliers, demonstrates the versatility of our approach and shows that compared to the accurate design, our control variate approximation achieves the same performance, 45% power reduction, and less than 1% average accuracy loss. Compared to the corresponding approximate designs without using our technique, our approach improves the accuracy by 1.9x on average.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。