Block-based neural networks

This paper presents a novel block-based neural network (BBNN) model and the optimization of its structure and weights based on a genetic algorithm. The architecture of the BBNN consists of a 2D array of fundamental blocks with four variable input/output nodes and connection weights. Each block can h...

Full description

Saved in:
Bibliographic Details
Published in:IEEE transaction on neural networks and learning systems 2001-03, Vol.12 (2), p.307-317
Main Authors: Moon, S W, Kong, S G
Format: Article
Language:English
Subjects:
Arrays
Blocking
Computer simulation
Encoding
Field programmable gate arrays
Genetic algorithms
Hardware
Logic
Mobile robots
Neural networks
Pattern classification
Programmable logic arrays
Reconfigurable logic
Robot control
Two dimensional
Citations: Items that this one cites
Items that cite this one
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:This paper presents a novel block-based neural network (BBNN) model and the optimization of its structure and weights based on a genetic algorithm. The architecture of the BBNN consists of a 2D array of fundamental blocks with four variable input/output nodes and connection weights. Each block can have one of four different internal configurations depending on the structure settings, The BBNN model includes some restrictions such as 2D array and integer weights in order to allow easier implementation with reconfigurable hardware such as field programmable logic arrays (FPGA). The structure and weights of the BBNN are encoded with bit strings which correspond to the configuration bits of FPGA. The configuration bits are optimized globally using a genetic algorithm with 2D encoding and modified genetic operators. Simulations show that the optimized BBNN can solve engineering problems such as pattern classification and mobile robot control.
ISSN:1045-9227
2162-237X
1941-0093
2162-2388
DOI:10.1109/72.914525