基于忆阻器的原位卷积策略用于精确盲文识别
Memristor-based in-situ convolutional strategy for accurate braille recognition
张翔鸿 1覃琮尧 2彭文鸿 2秦宁浦 2程恩平 2吴建鑫 2范裕阳 2杨倩 3陈惠鹏4
作者信息
- 1. Institute of Optoelectronic Display,National & Local United Engineering Lab of Flat Panel Display Technology,Fuzhou University,Fuzhou 350002,China;State Key Laboratory of ASIC and System,School of Microelectronics,Fudan University,Shanghai 200433,China
- 2. Institute of Optoelectronic Display,National & Local United Engineering Lab of Flat Panel Display Technology,Fuzhou University,Fuzhou 350002,China
- 3. Institute of Optoelectronic Display,National & Local United Engineering Lab of Flat Panel Display Technology,Fuzhou University,Fuzhou 350002,China;Zhicheng College,Fuzhou University,Fuzhou 350002,China
- 4. Institute of Optoelectronic Display,National & Local United Engineering Lab of Flat Panel Display Technology,Fuzhou University,Fuzhou 350002,China;Fujian Science & Technology Innovation Laboratory for Optoelectronic Information of China,Fuzhou 350100,China
- 折叠
摘要
大数据时代下,提高信号处理效率至关重要.由于传统计算架构的计算设备中存储单元和计算单元相互分离,未来将面临着计算效率的限制.基于多电导态器件的阵列电路可实现全硬件卷积神经网络(CNNs),具备提高计算效率的潜力.然而,在处理大规模卷积计算时,仍存在大量器件冗余,导致计算功耗低、计算成本高.本文创新性地提出了一种基于忆阻器的器件级原位卷积策略:以忆阻器的导电丝、掺杂面积和极化面积等的动态变化作为卷积运算过程,单个器件的电导切换所需的时间作为计算结果,通过忆阻器独特的尖峰数字信号体现卷积计算.通过忆阻器将复杂的模拟信号合理地编码为简单的数字信号,成功在单个器件上完成了卷积计算,这对于复杂信号处理和计算效率提高至关重要.在器件级原位卷积计算的基础上,本文进一步实现了盲文信号的特征识别和噪声过滤.本文所提的基于单个忆阻器的器件级原位卷积计算,将推动具有大规模卷积计算能力的复杂CNNs的构建,促进神经形态计算领域的创新和发展.
Abstract
Signal processing has entered the era of big data,and improving processing efficiency becomes crucial.Traditional computing architectures face computational effi-ciency limitations due to the separation of storage and com-putation.Array circuits based on multi-conductor devices enable full hardware convolutional neural networks(CNNs),which hold great potential to improve computational effi-ciency.However,when processing large-scale convolutional computations,there is still a significant amount of device re-dundancy,resulting in low computational power consumption and high computational costs.Here,we innovatively propose a memristor-based in-situ convolutional strategy,which uses the dynamic changes in the conductive wire,doping area,and polarization area of memristors as the process of convolu-tional operations,and uses the time required for conductance switching of a single device as the computation result,em-bodying convolutional computation through the unique spiked digital signal of the memristor.Our strategy reasonably encodes complex analog signals into simple digital signals through a memristor,completing the convolutional compu-tation at the device level,which is essential for complex signal processing and computational efficiency improvement.Based on the implementation of device-level convolutional comput-ing,we have achieved feature recognition and noise filtering for braille signals.We believe that our successful im-plementation of convolutional computing at the device level will promote the construction of complex CNNs with large-scale convolutional computing capabilities,bringing innova-tion and development to the field of neuromorphic comput-ing.
关键词
convolutional computing/multi-conductor/mem-ristor/conductive filamentsKey words
convolutional computing/multi-conductor/mem-ristor/conductive filaments引用本文复制引用
出版年
2024
NETL
NSTL
万方数据