th and excellent retention has bee'/> An Energy Efficient FinFET-based Field Programmable Synapse Array (FPSA) Feasible for One-shot Learning on EDGE AI
首页> 外文会议>IEEE Symposium on VLSI Technology >An Energy Efficient FinFET-based Field Programmable Synapse Array (FPSA) Feasible for One-shot Learning on EDGE AI
【24h】

An Energy Efficient FinFET-based Field Programmable Synapse Array (FPSA) Feasible for One-shot Learning on EDGE AI

机译:一种基于FinFET的高能效现场可编程突触阵列(FPSA),可在EDGE AI上进行单次学习

获取原文

摘要

A pure logic 14nm FinFET with capabilities of linearly tunable Vth and excellent retention has been implemented as synapses in neuromorphic system. For the first time, a Field Programmable Synapse Array (FPSA) has been adopted to replace conventional R-based memory Synapse Array (RSA). Thanks to the wide range of Vt-tuning ability, 200X on/off ratio, and the ultra-small variability, 12%, results showed that the training power and SN ratio of FPSA are 10 times and 50 times smaller than those of the RSA, respectively. Two applications were demonstrated on FPSA array for one-shot learning applications. First, FPSA is used to detect handwritten digits of MNIST dataset. "Learned it by once" can be achieved in this task. Furthermore, FPSA has been applied to recognize goldfish in Cifar 100 dataset after learned the other 4 fish species. With the assistance from one-shot learning, results show the machine learned it faster and better on EDGE. This demonstrates the feasibility of FPSA for low-power and cost-effective synapse-based one-shot learning applications in the AIoT era.
机译:具有线性可调V功能的纯逻辑14nm FinFET 并在神经形态系统中作为突触实现了出色的保留。首次采用了现场可编程突触阵列(FPSA)来代替传统的基于R的内存突触阵列(RSA)。得益于广泛的V t 调谐能力为200倍的开/关比,以及12%的超小变异性,结果表明FPSA的训练能力和信噪比分别比RSA的小10倍和50倍。在FPSA阵列上演示了两个应用程序,用于单次学习应用程序。首先,FPSA用于检测MNIST数据集的手写数字。在此任务中可以实现“一次学习”。此外,在了解了其他4种鱼类之后,FPSA已被用于识别Cifar 100数据集中的金鱼。在一次学习的帮助下,结果表明该机器在EDGE上学习得更快,更好。这证明了FPSA在AIoT时代用于低功耗和经济高效的基于突触的一次性学习应用程序的可行性。

著录项

相似文献

  • 外文文献
  • 专利
获取原文

客服邮箱:kefu@zhangqiaokeyan.com

京公网安备:11010802029741号 ICP备案号:京ICP备15016152号-6 六维联合信息科技 (北京) 有限公司©版权所有
  • 客服微信

  • 服务号