Conference paper Open Access

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

Domen Vake; Aleksandar Tošić; Jernej Vičič

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.

Pages 61-64
Files (5.3 MB)
Name Size
IS2019_Volume_C - SiKDD (1).pdf
md5:5cf0778e78e5f6ef27d1142b69aac91c
5.3 MB Download
38
48
views
downloads
All versions This version
Views 3838
Downloads 4848
Data volume 255.8 MB255.8 MB
Unique views 3636
Unique downloads 4747

Share

Cite as