低功耗神经网络芯片实现高效图像分类，能效比提升6.8倍。
An Energy-Efficient Adiabatic Capacitive Neural Network Chip
- 采用混合信号绝热电容架构，130nm工艺实现低功耗计算。
- 在8×8一比特图像上分类准确率超95%，误差仅2.7%。
- 适合电池供电的边缘设备，尤其适用于视频与传感场景。
人工智能的快速发展，以及视频处理和高分辨率传感等应用对数据带宽需求的增加，催生了在严格能耗限制下实现高性能计算的需求，特别是在电池供电和边缘设备中。为应对这一挑战，我们提出了一种在130nm CMOS工艺下设计的混合信号绝热电容神经网络芯片，显著降低能耗的同时保持高图像分类精度。该双层硬件芯片包含16个单周期乘加单元，可可靠区分4类8×8一比特图像，分类结果超过95%，与等效软件版本相比误差仅为2.7%。能量测量显示，相比等效的CMOS电容实现，平均节能2.1至6.8倍。
原文摘要 · Abstract (English)
Recent advances in artificial intelligence, coupled with increasing data bandwidth requirements, in applications such as video processing and high-resolution sensing, have created a growing demand for high computational performance under stringent energy constraints, especially for battery-powered and edge devices. To address this, we present a mixed-signal adiabatic capacitive neural network chip, designed in a 130$nm$ CMOS technology, to demonstrate significant energy savings coupled with high image classification accuracy. Our dual-layer hardware chip, incorporating 16 single-cycle multiply-accumulate engines, can reliably distinguish between 4 classes of 8x8 1-bit images, with classification results over 95\%, within 2.7\% of an equivalent software version. Energy measurements reveal average energy savings between 2.1x and 6.8x, compared to an equivalent CMOS capacitive implementation.
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。