arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2606.14739cs.ETcs.LGcs.SYeess.SY
收藏

基于RRAM的径向基函数神经元硬件实现用于边缘分类器

An RRAM-based Hardware Implementation of a Radial Basis Function Neuron for Edge Classifiers

Centre for Electronics Frontiers, Institute of Micro and Nano Systems(电子前沿中心,微纳系统研究所)

Georgios Papandroulidakis, Shady Agwa, Themis Prodromakis

AI总结:

提出一种基于金属氧化物RRAM的模拟内容可寻址存储器(ACAM)硬件设计,通过可配置感受野神经元实现边缘设备上的度量分类和在线自适应,在MNIST上达到89.1%准确率,每单元每操作能耗185fJ。

摘要:

现代机器学习(ML)解决方案在资源受限的边缘设备上的部署凸显了实现挑战。对于包含安全关键组件(如自主导航任务)的极端边缘应用尤其如此。本文展示了一种人工神经网络(ANN)设计,利用基于金属氧化物电阻式RAM(RRAM)的模拟内容可寻址存储器(ACAM)作为高效的硬件基础,用于在边缘执行基于度量的分类和在线自适应。所提出的设计基于用于构建ACAM模块的自定义模板像素(TXL)单元,其中每个TXL单元充当可配置的感受野神经元。这些单元采用径向基激活函数来计算输入与编程感受野的距离。TXL可以组织成密集阵列,用于计算高维输入与所有存储原型之间的距离,从而有效执行快速且节能的相似性搜索。该硬件引擎支持即时学习,其中感受野参数可以调整以跟踪域偏移。通过模拟所提出的TXL-RBF分类器,我们在MNIST数据集上实现了89.1%的准确率,同时在100MHz运行时每单元每操作消耗185fJ。

英文摘要:

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 10MHz.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑