高纠正比率自纠正的memristor交叉阵列用于卷积神经网络操作
Jiang Zhao1, Yingfang Zhu2, Shaoan Yan2
1School of Materials Science and Engineering, Xiangtan University, Xiangtan, Hunan, 411105, China.
Small (Weinheim an der Bergstrasse, Germany)
|April 25, 2025
概括
本研究介绍了一种用于神经网络的1kbit自我校正的memristor阵列. 该阵列可以抑制寄生电流,从而实现高识别精度的高效全硬件卷积神经网络 (CNN) 计算.
科学领域:
- 材料科学 材料科学 材料科学
- 计算机工程 计算机工程
- 人工智能的人工智能
背景情况:
- 基于氧化物的自我纠正记忆器为神经网络提供了优势,包括高密度和低功耗.
- 大型memristor阵列中的寄生电流阻碍了复杂神经网络的发展.
研究的目的:
- 开发一个1kbit的自我纠正的memristor阵列来抑制寄生电流.
- 用memristor数组来证明全硬件卷积神经网络 (CNN) 计算的可行性.
主要方法:
- 使用Pt/HfO2/Ti结构单元制造一个1kbit的memristor阵列.
- 描述单个设备的性能,包括切换和纠正比率.
- 对8位神经网络的卷积计算逻辑和前向推理的演示.
主要成果:
- 记忆器阵列显示的切换比率> 10^3 和纠正比率> 10^5.5.
- 优良的负校正有效地抑制了潜在路径电流.
- 一个完整的CNN系统在手写识别任务中实现了98%的识别率.
结论:
- 开发的memristor阵列可以有效地抑制寄生电流,从而实现高效的全硬件CNN实现.
- 这项工作为CNN实现全硬件计算提供了一个新的策略.
- 该系统在手写识别方面表现出高性能,验证了该方法.
相关概念视频
Neural Circuits
919
Neural circuits and neuronal pools are two of the main structures found in the nervous system. Neural circuits are networks of neurons that work together to carry out a specific task or process. They consist of interconnected neurons and glial cells, which provide structural and metabolic support.
Neuronal pools are collections of nerve cells with similar functions and interact through chemical and electrical signals. These pools include both interneurons (the central neural circuit nodes that...
Neuronal pools are collections of nerve cells with similar functions and interact through chemical and electrical signals. These pools include both interneurons (the central neural circuit nodes that...
919
MOS Capacitor
625
A Metal-Oxide-Semiconductor (MOS) capacitor is a fundamental structure used extensively in semiconductor device technology, particularly in the fabrication of integrated circuits and MOSFETs (metal-oxide-semiconductor field-effect transistors). The MOS capacitor consists of three layers: a metal gate, a dielectric oxide, and a semiconductor substrate.
The metal gate is typically made from highly conductive materials such as aluminum or polysilicon. Beneath the metal gate lies a thin layer of...
The metal gate is typically made from highly conductive materials such as aluminum or polysilicon. Beneath the metal gate lies a thin layer of...
625
Design Example: Capacitance Multiplier Circuit
614
In integrated circuit technology, a capacitance multiplier is often utilized to produce a larger capacitance value when a small physical capacitance falls short. This is achieved by a circuit that multiplies capacitance values by a factor of up to 1000, such that a 10-pF capacitor can replicate the performance of a 100-nF capacitor.
The circuit illustrated in Figure 1 below incorporates two op-amps, with the first operating as a voltage follower and the second acting as an inverting amplifier.
The circuit illustrated in Figure 1 below incorporates two op-amps, with the first operating as a voltage follower and the second acting as an inverting amplifier.
614
Bridge rectifier
399
The bridge rectifier is essential in electronics for efficiently converting alternating current (AC) to direct current (DC). Comprised of four diodes configured in a bridge layout, this rectifier effectively processes both the positive and negative halves of the AC waveform, making it superior to half-wave and full-wave center-tapped rectifiers in terms of voltage regulation and output stability.
Operationally, the bridge rectifier allows current flow through two of its diodes during each...
Operationally, the bridge rectifier allows current flow through two of its diodes during each...
399
Convolution Properties I
118
Convolution computations can be simplified by utilizing their inherent properties.
The commutative property reveals that the input and the impulse response of an LTI (Linear Time-Invariant) system can be interchanged without affecting the output:
The commutative property reveals that the input and the impulse response of an LTI (Linear Time-Invariant) system can be interchanged without affecting the output:
118
Convolution Properties II
146
The important convolution properties include width, area, differentiation, and integration properties.
The width property indicates that if the durations of input signals are T1 and T2, then the width of the output response equals the sum of both durations, irrespective of the shapes of the two functions. For instance, convolving two rectangular pulses with durations of 2 seconds and 1 second results in a function with a width of 3 seconds.
The area property asserts that the area under the...
The width property indicates that if the durations of input signals are T1 and T2, then the width of the output response equals the sum of both durations, irrespective of the shapes of the two functions. For instance, convolving two rectangular pulses with durations of 2 seconds and 1 second results in a function with a width of 3 seconds.
The area property asserts that the area under the...
146


