Evolutionary spiking neural networks as racing car controllers

Yee, Elias and Teo, Jason Tze Wi (2011) Evolutionary spiking neural networks as racing car controllers. In: 2011 11th International Conference on Hybrid Intelligent Systems, HIS 2011, 5-8 December 2011, Malacca, Malaysia.

Full text not available from this repository.


The Izhikevich spiking neural network model is investigated as a method to develop controllers for a simple, but not trivial, car racing game, called TORCS. The controllers are evolved using Evolutionary Programming, and the performance of the best individuals is compared with the hand-coded controller included with the Simulated Car Racing Championship API. The results are promising, indicating that this neural network model can be applied to other games or control problems.

Item Type: Conference or Workshop Item (UNSPECIFIED)
Keyword: Car racing, Evolutionary programming, Games, Izhikevich neuron model, Spiking neural networks, TORCS
Subjects: Q Science > QA Mathematics > QA1-939 Mathematics > QA71-90 Instruments and machines > QA75.5-76.95 Electronic computers. Computer science
Department: SCHOOL > School of Engineering and Information Technology
Depositing User: ADMIN ADMIN
Date Deposited: 10 May 2012 17:13
Last Modified: 08 Sep 2014 16:43
URI: https://eprints.ums.edu.my/id/eprint/4107

Actions (login required)

View Item View Item