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

Using coherent pulse width and edge modulations in artificial neural systems

L M Reyneri1, M Chiaberge, D Del Corso

  • 1Dipartimento di Elettronica, Politecnico di Torino, Italy.

International Journal of Neural Systems
|December 1, 1993
PubMed
Summary

This study presents a novel silicon artificial neural system using pulse modulation. The reconfigurable 32x32 synaptic array chip optimizes low-power robotic sensor and actuator interfacing.

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

Unification of neural and wavelet networks and fuzzy systems.

IEEE transactions on neural networks·2008
Same author

Implementation issues of neuro-fuzzy hardware: going toward HW/SW codesign.

IEEE transactions on neural networks·2008
Same author

Simulink-based HW/SW codesign of embedded neuro-fuzzy systems.

International journal of neural systems·2000
Same author

A hardware implementation of a biological neural system for target localization.

IEEE transactions on neural networks·1994
Same author

Pulse-stream VLSI neural networks mixing analog and digital techniques.

IEEE transactions on neural networks·1991

Area of Science:

  • Neuromorphic Engineering
  • Integrated Circuit Design
  • Robotics

Background:

  • Artificial neural systems are key for advanced computation.
  • Efficient hardware implementations are crucial for real-time applications.
  • Interfacing diverse sensors with neural systems presents challenges.

Purpose of the Study:

  • To describe a silicon implementation of an artificial neural system.
  • To optimize neural circuits for low power consumption and high reconfigurability.
  • To address the interfacing of robotic sensors and actuators with the neural system.

Main Methods:

  • Utilized coherent pulse width and edge modulation techniques for neural functions.
  • Designed, manufactured, and tested a chip set with a 32x32 synaptic array.

Related Experiment Videos

  • Investigated interfacing methods for voltage, current, and resistance-based sensors, including low-resolution imaging sensors.

    • Main Results:

    • Developed a 32x32 synaptic array chip consuming 10 mW at 140 MCPS.
    • Achieved small synapse size (7.200 microns^2) using 1.5 microns CMOS technology.
    • Addressed the integration of various robotic sensors and actuators.

    Conclusions:

    • The developed silicon artificial neural system offers efficient and reconfigurable computation.
    • The chip set effectively interfaces with diverse robotic sensors and actuators.
    • This work advances low-power, high-performance neuromorphic hardware for robotics.