”Extreme edge“ devices such as smart sensors are a uniquely challenging environment for the deployment of machine learning. The tiny energy budgets of these devices lie beyond what is feasible for conventional deep neural networks, particularly in high-throughput scenarios, requiring us to rethink how we approach edge inference. In this work, we propose ULEEN, a model and FPGA-based accelerator architecture based on weightless neural networks (WNNs). WNNs eliminate energy-intensive arithmetic operations, instead using table lookups to perform computation, which makes them theoretically well-suited for edge inference. However, WNNs have historically suffered from poor accuracy and excessive memory usage. ULEEN incorporates algorithmic improvements and a novel training strategy inspired by binary neural networks (BNNs) to make significant strides in addressing these issues. We compare ULEEN against BNNs in software and hardware using the four MLPerf Tiny datasets and MNIST. Our FPGA implementations of ULEEN accomplish classification at 4.0-14.3 million inferences per second, improving area-normalized throughput by an average of 3.6 × and steady-state energy efficiency by an average of 7.1 × compared to the FPGA-based Xilinx FINN BNN inference platform. While ULEEN is not a universally applicable machine learning model, we demonstrate that it can be an excellent choice for certain applications in energy- and latency-critical edge environments.

智能传感器等“极端边缘”设备对于机器学习的部署来说是一个独特的具有挑战性的环境。这些设备的微小能量预算超出了传统深度神经网络的可行性，特别是在高吞吐量场景中，要求我们重新思考如何进行边缘推理。在这项工作中，我们提出了 ULEEN，一种基于失重神经网络 (WNN) 的模型和基于 FPGA 的加速器架构。WNN 消除了能源密集型算术运算，而是使用表查找来执行计算，这使得它们在理论上非常适合边缘推理。然而，WNN 历史上一直存在准确性差和内存使用过多的问题。ULEEN 结合了算法改进和受二元神经网络 (BNN) 启发的新颖训练策略，在解决这些问题方面取得了重大进展。我们使用四个 MLPerf Tiny 数据集和 MNIST 将 ULEEN 与 BNN 在软件和硬件方面进行比较。与基于 FPGA 的 Xilinx FINN BNN 推理平台相比，我们的 ULEEN FPGA 实现以每秒 4.0-1430 万次推理的速度完成分类，将面积归一化吞吐量平均提高了 3.6 倍，稳态能源效率平均提高了 7.1 倍。虽然 ULEEN 不是普遍适用的机器学习模型，但我们证明它对于能源和延迟关键边缘环境中的某些应用程序来说是一个绝佳的选择。