An Analysis of Overfitting in Particle Swarm Optimised Neural Networks

An Analysis of Overfitting in Particle Swarm Optimised Neural Networks

The phenomenon of overfitting, where a feed-forward neural network (FFNN) over trains on training data at the cost of generalisation accuracy is known to be speci c to the training algorithm used. This study investigates over tting within the context of particle swarm optimised (PSO) FFNNs. Two o...

Full description

Bibliographic Details
Main Author: van Wyk, Andrich Benjamin
Other Authors: Engelbrecht, Andries P.
Language:en
Published: University of Pretoria 2015
Subjects:
UCTD
Particle swarm optimization (PSO)
Feedforward neural networks
Overfitting
Adaptive neural networks
Online Access:http://hdl.handle.net/2263/46273
van Wyk, AB 2014, An Analysis of Overfitting in Particle Swarm Optimised Neural Networks, MSc Dissertation, University of Pretoria, Pretoria, viewed yymmdd <http://hdl.handle.net/2263/46273>

Internet

http://hdl.handle.net/2263/46273
van Wyk, AB 2014, An Analysis of Overfitting in Particle Swarm Optimised Neural Networks, MSc Dissertation, University of Pretoria, Pretoria, viewed yymmdd <http://hdl.handle.net/2263/46273>

Similar Items