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 Experiment Videos

FangTianSim: High-Level Cycle-Accurate Resistive Random-Access Memory-Based Multi-Core Spiking Neural Network

Jinsong Wei1,2, Zhibin Wang1, Ye Li1

  • 1Zhejiang Laboratory, Institute of Intelligent Computing, Hangzhou, China.

Frontiers in Neuroscience
|February 7, 2022
PubMed
Summary

Related Concept Videos

You might also read

Related Articles

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

Sort by
Same author

Homoharringtonine, aclarubicin and cytarabine (HAA) regimen as the first course of induction therapy is highly effective for acute myeloid leukemia with t (8;21).

Leukemia research·2016
Same author

[Morphology and Spectral Properties Study of LaCeF3:Tb Microcrystalline].

Guang pu xue yu guang pu fen xi = Guang pu·2016
Same author

A highly selective fluorogenic probe for the detection and in vivo imaging of Cu/Zn superoxide dismutase.

Chemical communications (Cambridge, England)·2016
Same author

Development of a disaggregation-induced emission probe for the detection of RecA inteins from Mycobacterium tuberculosis.

Chemical communications (Cambridge, England)·2016
Same author

Bias-polarity-dependent resistance switching in W/SiO2/Pt and W/SiO2/Si/Pt structures.

Scientific reports·2016
Same author

Sequential Anaerobic/Aerobic Digestion for Enhanced Carbon/Nitrogen Removal and Cake Odor Reduction.

Water environment research : a research publication of the Water Environment Federation·2016

A new simulation model, FangTianSim, addresses challenges in designing energy-efficient spiking neural network (SNN) hardware. It verifies functionalities, delay, and power consumption for AI and IoT applications.

Area of Science:

  • * Neuromorphic Engineering
  • * Computer Architecture
  • * Materials Science

Background:

  • * Spiking Neural Networks (SNNs) offer energy-efficient solutions for Internet of Things (IoT) and Artificial Intelligence (AI).
  • * Resistive Random-Access Memory (RRAM) enables high-density, low-power Processing-in-Memory (PIM) for SNN hardware.
  • * Designing hybrid RRAM-based SNN chips faces challenges in pulse transmission, hybrid integration, and non-ideal device characteristics.

Purpose of the Study:

  • * To develop a comprehensive simulation model, FangTianSim, bridging device, circuit, algorithm, and architecture levels for RRAM-based SNN chips.
  • * To verify the functionalities, delay, and power consumption of multi-core SNN chips at the clock level.
  • * To guide the design and verify the rationality of RRAM-based SNN architectures.
Keywords:
RRAM (memristor)SystemCanalog circuitssimulatorspiking neural network (SNN)

Related Experiment Videos

Main Methods:

  • * Development of FangTianSim, a simulation model integrating analog neuron circuits, RRAM models, and multi-core architectures.
  • * Design of SNN representation formats, interpreters, and instruction generators for mapping diverse network topologies.
  • * Clock-level accuracy verification of the simulation model.

Main Results:

  • * FangTianSim accurately simulates RRAM-based SNN chip functionalities, delay, and power consumption.
  • * The model facilitates the verification of multi-core architecture rationality.
  • * Successful functional verification on Liquid State Machine (LSM), Fully Connected Neural Network (FCNN), and Convolutional Neural Network (CNN) topologies.

Conclusions:

  • * FangTianSim provides a crucial tool for advancing the design of highly integrated and energy-efficient SNN hardware.
  • * The simulation model aids in overcoming key design challenges in RRAM-based SNN chips.
  • * This work supports the development of next-generation AI and IoT systems leveraging SNNs.