SenTer: A Reconfigurable Processing-in-Sensor Architecture Enabling Efficient Ternary MLP
SenTer: A Reconfigurable Processing-in-Sensor Architecture Enabling Efficient Ternary MLP
复制标题
DOI：
10.1145/3583781.3590225
复制
发表时间：
2023-06
期刊：
影响因子：
--
通讯作者：
Sepehr Tabrizchi;Rebati Gaire;Shaahin Angizi;A. Roohi
中科院分区：
文献类型：
--
作者：
Sepehr Tabrizchi;Rebati Gaire;Shaahin Angizi;A. Roohi
最近，包括各种传感器在内的智能物联网（IIoT）由于其利用人工神经网络（ANN）进行感知、决策和行动的能力而受到了极大的关注。然而，为了在视觉系统中达到可接受的精度和高性能，需要一个节能的功耗延迟架构。在本文中，我们提出了一种超低功耗的传感器内处理架构，即SenTer，它实现了低精度的三元多层感知器网络，可以在检测和分类模式下运行。此外，SenTer还支持基于用户需求的两种激活功能和期望的精度-能量权衡。SenTer能够在模拟域中执行MLP第一层所需的所有计算，然后将其结果提交给协处理器。因此，SenTer通过仅使用一个ADC显著降低了模拟缓冲区的开销、数据转换和传输功耗。此外，与全精度模型相比，我们的模拟结果在各种数据集上显示出可接受的精度。
Recently, Intelligent IoT (IIoT), including various sensors, has gained significant attention due to its capability of sensing, deciding, and acting by leveraging artificial neural networks (ANN). Nevertheless, to achieve acceptable accuracy and high performance in visual systems, a power-delay-efficient architecture is required. In this paper, we propose an ultra-low-power processing in-sensor architecture, namely SenTer, realizing low-precision ternary multi-layer perceptron networks, which can operate in detection and classification modes. Moreover, SenTer supports two activation functions based on user needs and the desired accuracy-energy trade-off. SenTer is capable of performing all the required computations for the MLP's first layer in the analog domain and then submitting its results to a co-processor. Therefore, SenTer significantly reduces the overhead of analog buffers, data conversion, and transmission power consumption by using only one ADC. Additionally, our simulation results demonstrate acceptable accuracy on various datasets compared to the full precision models.