Related Experiment Video
Updated: Jul 6, 2025
08:07
Assembly and Characterization of Biomolecular Memristors Consisting of Ion Channel-doped Lipid Membranes
Published on: March 9, 2019
7.8K
Implementation of Convolutional Neural Networks in Memristor Crossbar Arrays with Binary Activation and Weight
Jinwoo Park1, Sungjoon Kim2, Min Suk Song1
1Department of Electrical and Computer Engineering, Inha University, Incheon 22212, Korea.
ACS Applied Materials & Interfaces
|January 1, 2024
Summary
We developed a hardware-friendly convolutional neural network using a memristor crossbar array. This novel architecture enables efficient 3-bit multilevel operations for advanced artificial intelligence hardware.
Area of Science:
- Neuromorphic Engineering
- Materials Science
- Computer Science
Background:
- Memristor crossbar arrays offer a promising platform for efficient hardware acceleration of neural networks.
- Implementing multilevel operations and robust activation functions in memristor-based systems remains a challenge.
- Optimizing hardware architectures to minimize device variability and maximize utilization is crucial for practical applications.
Purpose of the Study:
- To propose and evaluate a hardware-friendly convolutional neural network architecture utilizing a memristor crossbar array.
- To implement 3-bit multilevel operations and a binary activation function for enhanced computational efficiency.
- To demonstrate the feasibility of vector-matrix multiplication and classification using the proposed memristor-based system.
Main Methods:
- A 32x32 memristor crossbar array with an overshoot suppression layer was designed.
- A 3-bit multilevel operation was implemented across the array, supporting 16 kernels.
- A binary activation function and a fixed kernel method with sequential input application were employed.
- Vector-matrix multiplication (VMM) operations were experimentally demonstrated using memristor devices.
- A neuron circuit was experimentally validated on a breadboard.
Main Results:
- The architecture successfully implemented 3-bit multilevel operations and a binary activation function.
- Accurate VMM operations were achieved due to the analog switching characteristics of memristors.
- Hardware inference was performed on test samples, and classification performance was compared to software results.
- The fixed kernel method effectively reduced unused cell waste.
- The binary activation function demonstrated robustness against device state variations.
Conclusions:
- The proposed memristor crossbar array architecture provides a hardware-friendly solution for efficient neural network implementation.
- The system demonstrates the potential for accurate VMM and classification tasks in neuromorphic computing.
- The study validates the use of memristors for multilevel operations and robust activation functions in AI hardware.
Related Concept Videos
01:25MOS Capacitor
789
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...
789
01:24Convolution: Math, Graphics, and Discrete Signals
263
In any LTI (Linear Time-Invariant) system, the convolution of two signals is denoted using a convolution operator, assuming all initial conditions are zero. The convolution integral can be divided into two parts: the zero-input or natural response and the zero-state or forced response, with t0 indicating the initial time.
To simplify the convolution integral, it is assumed that both the input signal and impulse response are zero for negative time values. The graphical convolution process...
To simplify the convolution integral, it is assumed that both the input signal and impulse response are zero for negative time values. The graphical convolution process...
263
01:20Design Example: Capacitance Multiplier Circuit
779
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.
779
01:25Network Function of a Circuit
290
Frequency response analysis in electrical circuits provides vital insights into a circuit's behavior as the frequency of the input signal changes. The transfer function, a mathematical tool, is instrumental in understanding this behavior. It defines the relationship between phasor output and input and comes in four types: voltage gain, current gain, transfer impedance, and transfer admittance. The critical components of the transfer function are the poles and zeros.
290