Fitness Distance Correlation of Neural Network Error Surfaces: A Scalable, Continuous Optimization Problem

Authors:
Marcus Gallagher
Affiliations:
-
Venue:
EMCL '01 Proceedings of the 12th European Conference on Machine Learning
Year:
2001

Citing 6
Cited 0

Models for iterative global optimization

Models for iterative global optimization
Evaluating evolutionary algorithms

Artificial Intelligence - Special volume on empirical methods
Neural Smithing: Supervised Learning in Feedforward Artificial Neural Networks

Neural Smithing: Supervised Learning in Feedforward Artificial Neural Networks
Building Blocks, Cohort Genetic Algorithms, and Hyperplane-Defined Functions

Evolutionary Computation
A comparison of predictive measures of problem difficulty inevolutionary algorithms

IEEE Transactions on Evolutionary Computation
Test-case generator for nonlinear continuous parameter optimizationtechniques

IEEE Transactions on Evolutionary Computation

Quantified Score

Hi-index	0.01

Visualization

Abstract

This paper investigates neural network training as a potential source of problems for benchmarking continuous, heuristic optimization algorithms. Through the use of a student-teacher learning paradigm, the error surfaces of several neural networks are examined using so-called fitness distance correlation, which has previously been applied to discrete, combinatorial optimization problems. The results suggest that the neural network training tasks offer a number of desirable properties for algorithm benchmarking, including the ability to scale-up to provide challenging problems in high-dimensional spaces.