Search research articles

ABOUT JoVE

Overview Leadership Blog JoVE Help Center

AUTHORS

Publishing Process Editorial Board Scope & Policies Peer Review FAQ Submit

LIBRARIANS

Testimonials Subscriptions Access Resources Library Advisory Board FAQ

RESEARCH

JoVE Journal Methods Collections JoVE Encyclopedia of Experiments Archive

EDUCATION

JoVE Core JoVE Business JoVE Science Education JoVE Lab Manual Faculty Resource Center Faculty Site

Terms & Conditions of Use

Search research articles

Related Experiment Videos

Block-based neural networks.

S W Moon¹, S G Kong

¹Intelligent Signal Processing Lab, Department of Electrical Engineering, Soongsil University, Seoul 156-743, Korea.

IEEE Transactions on Neural Networks

|February 5, 2008

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

Parity and the risk of incident dementia: a COSMIC study.

Epidemiology and psychiatric sciences·2020

Same author

Disc degeneration induces a mechano-sensitization of disc afferent nerve fibers that associates with low back pain.

Osteoarthritis and cartilage·2019

Same author

Benign metastasising leiomyoma mistaken for pulmonary metastasis from an ovarian carcinoma.

Journal of obstetrics and gynaecology : the journal of the Institute of Obstetrics and Gynaecology·2014

Same author

Tension subcutaneous emphysema during laparoscopic surgery treatment of colon cancer: a case report.

The Thoracic and cardiovascular surgeon·2012

Same author

Potential effects of tooth-brushing on human dentin wear following exposure to acidic soft drinks.

Journal of microscopy·2012

Same author

Diagnostic radiopacity and hepatotoxicity following chloroform ingestion: a case report.

Emergency medicine journal : EMJ·2006

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

A novel block-based neural network (BBNN) optimized using a genetic algorithm offers efficient solutions for engineering tasks. This approach enables effective pattern classification and mobile robot control using reconfigurable hardware.

Area of Science:

Computational intelligence
Artificial neural networks
Hardware implementation

Background:

Traditional neural networks can be computationally intensive.
Implementing complex neural networks on reconfigurable hardware presents challenges.

Purpose of the Study:

To introduce a novel block-based neural network (BBNN) model.
To optimize the BBNN's structure and weights using a genetic algorithm for hardware implementation.

Main Methods:

Developed a BBNN with a 2D array of fundamental blocks and variable connections.
Utilized a genetic algorithm with 2D encoding and modified operators to optimize BBNN structure and integer weights.
Encoded BBNN configurations as bit strings compatible with Field-Programmable Logic Arrays (FPGAs).

Related Experiment Videos

Main Results:

The optimized BBNN demonstrated effectiveness in solving engineering problems.
Simulations confirmed the model's capability in pattern classification tasks.
The BBNN proved successful in mobile robot control applications.

Conclusions:

The proposed BBNN model, optimized via a genetic algorithm, is suitable for hardware implementation.
The approach allows for efficient solutions in complex engineering problems.
This method facilitates the use of neural networks on reconfigurable hardware like FPGAs.