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

Real-time neural network inversion on the SRC-6e reconfigurable computer.

Russell W Duren1, Robert J Marks, Paul D Reynolds

  • 1Department of Electrical and Computer Engineering, Baylor University, Waco, TX 76798, USA. Russell_W_Duren@baylor.edu

IEEE Transactions on Neural Networks
|May 29, 2007
PubMed
Summary
This summary is machine-generated.

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

Sampling below the Nyquist density using spectral subtiles.

Journal of the Optical Society of America. A, Optics, image science, and vision·2019
Same author

Design and Performance of a 1 mm<sup>3</sup> Resolution Clinical PET System Comprising 3-D Position Sensitive Scintillation Detectors.

IEEE transactions on medical imaging·2018
Same author

Characterization of a sub-assembly of 3D position sensitive cadmium zinc telluride detectors and electronics from a sub-millimeter resolution PET system.

Physics in medicine and biology·2016
Same author

Analog signal multiplexing for PSAPD-based PET detectors: simulation and experimental validation.

Physics in medicine and biology·2010
Same author

Convex optimization of coincidence time resolution for a high-resolution PET system.

IEEE transactions on medical imaging·2010
Same author

Emergent behaviors of protector, refugee, and aggressor swarms.

IEEE transactions on systems, man, and cybernetics. Part B, Cybernetics : a publication of the IEEE Systems, Man, and Cybernetics Society·2007
Same journal

Universal perceptron and DNA-like learning algorithm for binary neural networks: LSBF and PBF implementations.

IEEE transactions on neural networks·2013
Same journal

Guest editorial: special section on white box nonlinear prediction models.

IEEE transactions on neural networks·2011
Same journal

Data-based fault-tolerant control of high-speed trains with traction/braking notch nonlinearities and actuator failures.

IEEE transactions on neural networks·2011
Same journal

Guest editorial: special section on data-based control, modeling, and optimization.

IEEE transactions on neural networks·2011
Same journal

Neural network-based multiple robot simultaneous localization and mapping.

IEEE transactions on neural networks·2011
Same journal

Data-driven model-free adaptive control for a class of MIMO nonlinear discrete-time systems.

IEEE transactions on neural networks·2011
See all related articles

This study implements real-time neural network inversion on FPGA hardware for sonar systems. The optimized system achieves a significant speed increase, enabling real-time performance.

Area of Science:

  • Computational intelligence
  • Signal processing
  • Hardware acceleration

Background:

  • Real-time neural network inversion is crucial for dynamic systems like sonar.
  • Field-programmable gate arrays (FPGAs) offer potential for high-speed computation.

Purpose of the Study:

  • To implement and evaluate real-time neural network inversion on FPGA hardware.
  • To optimize sonar system performance using particle swarm optimization (PSO) on FPGAs.

Main Methods:

  • Utilized a feedforward multilayer perceptron neural network for sonar performance estimation.
  • Employed particle swarm optimization (PSO) for parameter search, requiring repetitive neural network queries.
  • Contrasted alternative implementations of neural networks and PSO on reconfigurable hardware.

Related Experiment Videos

Main Results:

  • Achieved nearly two orders of magnitude speed increase compared to a state-of-the-art personal computer (PC).
  • Demonstrated a viable real-time solution for neural network inversion and optimization in a sonar application.

Conclusions:

  • FPGA-based implementation of neural network inversion and PSO provides significant performance gains.
  • Real-time optimization of sonar systems is feasible with reconfigurable computing.