Jove
Visualize
Contact Us
JoVE
x logofacebook logolinkedin logoyoutube logo
ABOUT JoVE
OverviewLeadershipBlogJoVE Help Center
AUTHORS
Publishing ProcessEditorial BoardScope & PoliciesPeer ReviewFAQSubmit
LIBRARIANS
TestimonialsSubscriptionsAccessResourcesLibrary Advisory BoardFAQ
RESEARCH
JoVE JournalMethods CollectionsJoVE Encyclopedia of ExperimentsArchive
EDUCATION
JoVE CoreJoVE BusinessJoVE Science EducationJoVE Lab ManualFaculty Resource CenterFaculty Site
Terms & Conditions of Use
Privacy Policy
Policies

Related Concept Videos

MOS Capacitor01:25

MOS Capacitor

900
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...
900
Understanding Memory01:19

Understanding Memory

578
Memory is the retention of information or experiences over time, facilitated through three main processes: encoding, storage, and retrieval. Encoding is the process of inputting information into the memory system. For instance, when listening to a lecture, watching a play, reading a book, or having a conversation, the brain is actively encoding information. This initial stage involves transforming sensory input into a form that can be processed and stored by the brain. Various factors, such as...
578

You might also read

Related Articles

Articles linked to this work by shared authors, journal, and citation graph.

Sort by
Same author

In-Situ Constructed Cations for 2D/3D Perovskite Heterostructure for Stable and Efficient Photovoltaics.

Advanced science (Weinheim, Baden-Wurttemberg, Germany)·2026
Same author

Tumor-targeting semi-rigid metal-organic-polymer framework nanoparticles with high adaptability and bioavailability.

Journal of materials chemistry. B·2026
Same author

Fast-response electrophoretic display via particle size engineering.

Optics express·2026
Same author

Solution-Processed, In Situ Photopatternable Conducting Polymer Electrodes for High-Performance and Durable Electrowetting Displays.

Langmuir : the ACS journal of surfaces and colloids·2026
Same author

Picosecond-scale coherent toggle switching of topological spin helicity.

Nature nanotechnology·2026
Same author

Polyelectrolyte-Functionalized Corona-Shell Integration of Iron Oxide Nanoparticle for Electrophoretic Control.

ACS omega·2026

Related Experiment Video

Updated: Aug 13, 2025

Assembly and Characterization of Biomolecular Memristors Consisting of Ion Channel-doped Lipid Membranes
08:07

Assembly and Characterization of Biomolecular Memristors Consisting of Ion Channel-doped Lipid Membranes

Published on: March 9, 2019

7.9K

Performance estimation for the memristor-based computing-in-memory implementation of extremely factorized network for

Shuai Dong1, Zhen Fan1, Yihong Chen2

  • 1Institute for Advanced Materials, South China Academy of Advanced Optoelectronics, South China Normal University, Guangzhou, 510006, China; Guangdong Provincial Key Laboratory of Optical Information Materials and Technology, South China Academy of Advanced Optoelectronics, South China Normal University, Guangzhou, 510006, China.

Neural Networks : the Official Journal of the International Neural Network Society
|January 19, 2023
PubMed
Summary

This study introduces EFNet, a lightweight semantic segmentation model, and a memristor-based computing-in-memory accelerator. This algorithm-hardware co-design achieves high speed and energy efficiency for edge applications like autonomous driving.

Keywords:
Lightweight networkLow-powerMemristor-based CIM acceleratorReal-timeSemantic segmentation

More Related Videos

A Method for Growing Bio-memristors from Slime Mold
07:46

A Method for Growing Bio-memristors from Slime Mold

Published on: November 2, 2017

9.0K
Large Scale Energy Efficient Sensor Network Routing Using a Quantum Processor Unit
05:30

Large Scale Energy Efficient Sensor Network Routing Using a Quantum Processor Unit

Published on: September 8, 2023

632

Related Experiment Videos

Last Updated: Aug 13, 2025

Assembly and Characterization of Biomolecular Memristors Consisting of Ion Channel-doped Lipid Membranes
08:07

Assembly and Characterization of Biomolecular Memristors Consisting of Ion Channel-doped Lipid Membranes

Published on: March 9, 2019

7.9K
A Method for Growing Bio-memristors from Slime Mold
07:46

A Method for Growing Bio-memristors from Slime Mold

Published on: November 2, 2017

9.0K
Large Scale Energy Efficient Sensor Network Routing Using a Quantum Processor Unit
05:30

Large Scale Energy Efficient Sensor Network Routing Using a Quantum Processor Unit

Published on: September 8, 2023

632

Area of Science:

  • Computer Vision
  • Hardware Acceleration
  • Edge Computing

Background:

  • Current semantic segmentation algorithms struggle with speed and energy efficiency on edge devices.
  • Autonomous driving requires real-time, low-power visual perception.

Purpose of the Study:

  • To develop an efficient lightweight semantic segmentation algorithm for edge applications.
  • To design a hardware accelerator for improved speed and energy efficiency.
  • To demonstrate algorithm-hardware co-design for real-time edge semantic segmentation.

Main Methods:

  • Proposed an extremely factorized network (EFNet) for multi-scale context and spatial information preservation with reduced complexity.
  • Designed a memristor-based computing-in-memory (CIM) accelerator for EFNet hardware implementation.
  • Evaluated EFNet on the Cityscapes dataset and simulated the CIM accelerator using DNN+NeuroSim V2.0.

Main Results:

  • EFNet achieved 68.0% mIoU with 0.18M parameters at 99 FPS on an RTX 3090 GPU.
  • The memristor-based CIM accelerator showed significant improvements in area (up to 63x), speed (up to 9.2x), and energy efficiency (up to 470x) compared to GPU and embedded boards.
  • A slight accuracy decrease of 1.7% mIoU was observed with the CIM accelerator.

Conclusions:

  • EFNet is an effective lightweight semantic segmentation model.
  • Memristor-based CIM accelerators offer substantial advantages for edge deployment of semantic segmentation models.
  • Algorithm-hardware co-design is a promising approach for real-time, low-power edge AI.