BrainCrafter: An investigation into human-based neural network engineering

J. Piskur, P. Greve, J. Togelius, S. Risi

Publikation: Konference artikel i Proceeding eller bog/rapport kapitelKonferencebidrag i proceedingsForskningpeer review

Abstrakt

This paper presents the online application Brain-Crafter, in which users can manually build artificial neural networks (ANNs) to control a robot in a maze environment. Users can either start to construct networks from scratch or elaborate on networks created by other users. In particular, BrainCrafter was designed to study how good we as humans are at building ANNs for control problems and if collaborating with other users can facilitate this process. The results in this paper show that (1) some users were in fact able to successfully construct ANNs that solve the navigation tasks, (2) collaboration between users presented difficulties and (3) the human-developed ANNs that managed to solve the task had certain regularities, suggesting that humans can use some of their intuition and spatial understanding in the design of ANNs. Most importantly, the initial results in this paper can serve as a starting point for investigating how to best combine human and machine design capabilities to create more complex artificial brains.
OriginalsprogUdefineret/Ukendt
TitelEvolutionary Computation (CEC), 2015 IEEE Congress on
Antal sider8
ForlagIEEE
Publikationsdato1 maj 2015
Sider2199-2206
ISBN (Trykt)978-1-4799-7492-4
DOI
StatusUdgivet - 1 maj 2015

Emneord

  • human factors
  • neural nets
  • ANN
  • BrainCrafter
  • artificial neural networks
  • complex artificial brains
  • human design capabilities
  • human-based neural network engineering
  • machine design capabilities
  • Artificial neural networks
  • Biological neural networks
  • Collaboration
  • Navigation
  • Neurons
  • Robots
  • Sensors

Citationsformater