用阻变存储器实现快速低功耗的边缘分类神经元。
An RRAM-based Hardware Implementation of a Radial Basis Function Neuron for Edge Classifiers
- 用阻变存储器构建类内容寻址内存，实现径向基函数神经元。
- 在MNIST上达89.1%准确率，每操作仅耗电185fJ。
- 适合资源受限的边缘设备实时学习与自适应任务。
将现代机器学习部署于资源受限的边缘设备面临实现挑战，尤其在自动驾驶等安全关键场景中更为突出。本文提出一种基于金属氧化物阻变存储器（RRAM）的模拟内容寻址内存（ACAM）人工神经网络（ANN）设计，可在边缘端高效完成基于距离的分类与在线自适应。该设计采用定制的模板像素单元（TXL），每个单元作为可配置的感受野神经元，使用径向基函数计算输入与预设感受野的距离。这些单元可组织为密集阵列，对高维输入与所有存储原型进行快速相似性搜索，实现高效低功耗匹配。该硬件引擎支持即插即用的学习机制，可动态调整感受野参数以追踪领域漂移。仿真结果显示，在100MHz频率下，该TXL-RBF分类器在MNIST数据集上达到89.1%准确率，每单元每次操作仅消耗185fJ能量。
原文摘要 · Abstract (English)
The deployment of modern machine learning (ML) solutions on resource-constrained edge devices highlights implementation challenges. This is especially true for extreme edge applications that include safety-critical components, such as autonomous navigation tasks. This paper demonstrates an artificial neural network (ANN) design leveraging Metal-Oxide Resistive RAM (RRAM) -based Analogue Content Addressable Memory (ACAM) as an efficient hardware substrate for performing metric-based classification and online adaptation on the edge. The proposed design is based on a custom Template piXeL (TXL) cell used for building the ACAM module, where each TXL cell acts as a configurable receptive field neuron. These cells employ a Radial Basis activation function to calculate the distance of an input from the programmed receptive field. The TXL can be organised into dense arrays for calculating the distance of a high-dimensional input against all stored prototypes, effectively performing fast and energy efficient similarity search. This hardware engine enables on-the-fly learning, where the receptive field parameters can be tuned to track domain shift. Through simulation of the proposed TXL-RBF classifier we can achieve 89.1\% accuracy on the MNIST dataset while consuming 185fJ per cell per operation when operating at 100MHz.
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。