A parallel genetic/neural network learning algorithm for MIMD shared memory machines

Authors:
S. L. Hung;H. Adeli
Affiliations:
Dept. of Civil Eng., Nat. Chiao Tung Univ., Hsinchu;-
Venue:
IEEE Transactions on Neural Networks
Year:
1994

Citing 0
Cited 6

Improved and generalized learning strategies for dynamically fast and statistically robust evolutionary algorithms

Engineering Applications of Artificial Intelligence
A probabilistic neural network for earthquake magnitude prediction

Neural Networks
A coarse-grained parallel approach for seismic damage simulations of urban areas based on refined models and GPU/CPU cooperative computing

Advances in Engineering Software
Optimising operational costs using Soft Computing techniques

Integrated Computer-Aided Engineering
A model for mining material properties for radiation shielding

Integrated Computer-Aided Engineering
A computational intelligence optimization algorithm: Cloud drops algorithm

Integrated Computer-Aided Engineering

Quantified Score

Hi-index	0.00

Visualization

Abstract

A new algorithm is presented for training of multilayer feedforward neural networks by integrating a genetic algorithm with an adaptive conjugate gradient neural network learning algorithm. The parallel hybrid learning algorithm has been implemented in C on an MIMD shared memory machine (Cray Y-MP8/864 supercomputer). It has been applied to two different domains, engineering design and image recognition. The performance of the algorithm has been evaluated by applying it to three examples. The superior convergence property of the parallel hybrid neural network learning algorithm presented in this paper is demonstrated