期刊
IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS
卷 29, 期 10, 页码 4782-4790出版社
IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
DOI: 10.1109/TNNLS.2017.2778940
关键词
Deep learning; floating-gate memory cells; multilayer perceptron; neuromorphic networks; pattern classification
类别
资金
- DARPA's UPSIDE Program via BAE Systems, Inc. [HR0011-13-C-0051UPSIDE]
Potential advantages of analog-and mixed-signal nanoelectronic circuits, based on floating-gate devices with adjustable conductance, for neuromorphic computing had been realized long time ago. However, practical realizations of this approach suffered from using rudimentary floating-gate cells of relatively large area. Here, we report a prototype 28 x 28 binary-input, ten-output, three-layer neuromorphic network based on arrays of highly optimized embedded nonvolatile floating-gate cells, redesigned from a commercial 180-nm nor flash memory. All active blocks of the circuit, including 101 780 floating-gate cells, have a total area below 1 mm(2). The network has shown a 94.7% classification fidelity on the common Modified National Institute of Standards and Technology benchmark, close to the 96.2% obtained in simulation. The classification of one pattern takes a sub-1-mu s time and a sub-20-nJ energy-both numbers much better than in the best reported digital implementations of the same task. Estimates show that a straightforward optimization of the hardware and its transfer to the already available 55nm technology may increase this advantage to more than 10(2)x in speed and 10(4)x in energy efficiency.
作者
我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。
推荐
暂无数据