Related Experiment Video
Updated: Mar 31, 2026
09:49
In Situ Transmission Electron Microscopy with Biasing and Fabrication of Asymmetric Crossbars Based on Mixed-Phased a-VOx
Published on: May 13, 2020
4.4K
Comparative Study on Statistical-Variation Tolerance Between Complementary Crossbar and Twin Crossbar of Binary
Son Ngoc Truong1, SangHak Shin2, Sang-Don Byeon3
1School of Electrical Engineering, Kookmin University, 77, Jeongneung-ro, Seongbuk-gu, Seoul, 136-702, South Korea. sontn@kookmin.ac.kr.
Nanoscale Research Letters
|October 18, 2015
Summary
The twin crossbar architecture demonstrates superior statistical-variation tolerance compared to the complementary crossbar. This enhanced robustness leads to higher recognition rates for both greyscale images and alphabet characters under varying correlation conditions.
Area of Science:
- Electrical Engineering and Computer Science
- Materials Science
- Artificial Intelligence
Background:
- Crossbar architectures are fundamental in emerging memory and computing technologies.
- Statistical variations and correlations in circuit parameters significantly impact device performance and reliability.
- Understanding variation tolerance is crucial for designing robust and high-performance computing systems.
Purpose of the Study:
- To conduct a comparative analysis of statistical-variation tolerance between complementary and twin crossbar architectures.
- To evaluate the impact of varying statistical variation and correlation parameters on the recognition rates of these architectures.
- To determine which crossbar architecture exhibits superior robustness under different operational conditions.
Main Methods:
- A comparative study was performed on complementary and twin crossbar architectures.
- Circuit simulations were utilized to test the recognition rates.
- Ten greyscale images and 26 black-and-white alphabet characters were used as test datasets under varying inter-array and intra-array correlation parameters (0 and 1).
Main Results:
- The twin crossbar architecture consistently outperformed the complementary architecture in recognition rates across all tested conditions.
- For greyscale image recognition, the twin crossbar showed an average improvement of 4% (inter-array=1, intra-array=0) and 5.6% (inter-array=1, intra-array=1).
- For alphabet character recognition, the twin crossbar achieved average improvements of 4.5% (inter-array=1, intra-array=0) and 6% (inter-array=1, intra-array=1).
Conclusions:
- The twin crossbar architecture exhibits significantly higher robustness against statistical variations and correlations compared to the complementary crossbar.
- The findings suggest that the twin crossbar architecture is a more reliable choice for applications sensitive to statistical variations.
- This study provides valuable insights for the design and optimization of future crossbar-based computing systems.
Related Concept Videos
01:25MOS Capacitor
1.8K
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...
1.8K
01:23McNemar's Test
991
McNemar's Test is a nonparametric statistical test used to determine if there is a significant difference in proportions between two related groups when the outcome is binary (e.g., yes/no, success/failure). It is beneficial when we have paired data, such as pre-test/post-test designs, where the same subjects are measured under two different conditions. The test is named after the statistician Quinn McNemar, who introduced it in 1947. It is commonly used in situations where subjects are...
991
01:27Biasing of Metal-Semiconductor Junctions
815
Biasing metal-semiconductor junctions involves applying a voltage across the junction. Specifically, the metal is connected to a voltage source, while the semiconductor is grounded. This technique is essential for controlling the direction and magnitude of current flow in electronic devices, including diodes, transistors, and photovoltaic cells.
In Schottky junctions, where the semiconductor is n-type, applying a positive voltage to the metal relative to the semiconductor reduces its Fermi...
In Schottky junctions, where the semiconductor is n-type, applying a positive voltage to the metal relative to the semiconductor reduces its Fermi...
815
01:22Biasing of FET
928
Biasing a Junction Field Effect Transistor (JFET) is crucial for setting operational parameters and ensuring efficient functioning in electronic circuits. JFETs are characterized by using a single carrier type in N-channel or P-channel configurations, where the channel is surrounded by PN junctions. These junctions are central to the device's ability to control current flow.
In an N-channel JFET, the structure consists of N-type material forming the channel on a P-type substrate, with the...
In an N-channel JFET, the structure consists of N-type material forming the channel on a P-type substrate, with the...
928
01:17Characteristics of MOSFET
1.3K
Metal-oxide-semiconductor field-effect Transistors, or MOSFETs, play a critical role in electronic circuits. They are primarily utilized for amplifying and switching signals.
Various vital parameters influence their functionality, which is crucial for theory and electronics applications. First, channel dimensions, precisely length, and width, are pivotal. The size of these channels affects the transistor's ability to carry current and switching speeds; shorter channels typically enable...
Various vital parameters influence their functionality, which is crucial for theory and electronics applications. First, channel dimensions, precisely length, and width, are pivotal. The size of these channels affects the transistor's ability to carry current and switching speeds; shorter channels typically enable...
1.3K
01:19Equivalent Capacitance
2.4K
Multiple capacitors can be connected in a circuit in series or parallel configuration. When the capacitor combination is connected to a battery, the potential drop across each capacitor and the magnitude of charge stored in the individual capacitor depends on the type of the connection. The capacitor combination is replaced by a single equivalent capacitor that stores the same amount of charge as the combination for a given potential difference.
The following strategies are adopted to calculate...
The following strategies are adopted to calculate...
2.4K