Published October 7, 2019 | Version v1
Conference paper Open

Empirical study on the performance of Neuro Evolution of Augmenting Topologies (NEAT)

  • 1. Innorenew CoE
  • 2. Innorenew CoE; University of Primorska
  • 3. University of Primorska; ZRC-SAZU

Description

In this paper we provide empirical results on training a neural network with a genetic algorithm. We test various features of the generalized genetic algorithms, namely spieciation and fitness sharing and present the statistical analysis of all three variations. An obstacle avoidance problem was created in which the objective is for vehicles to traverse the course. We present interesting observations about the differences between evolutionary techniques and argue that there is a significant benefit in approaches that aim to diversify the gene pool as a mechanism for avoiding local minima.

Notes

Pages 61-64

Files

IS2019_Volume_C - SiKDD (1).pdf

Files (5.3 MB)

Name Size Download all
md5:5cf0778e78e5f6ef27d1142b69aac91c
5.3 MB Preview Download

Additional details

Identifiers

ISBN
978-961-264-160-3

Funding

InnoRenew CoE – Renewable materials and healthy environments research and innovation centre of excellence 739574
European Commission