Howto:Neural networks in Nasal: Difference between revisions

From FlightGear wiki
Jump to navigation Jump to search
m (some ideas)
 
Line 31: Line 31:


= Links =
= Links =
* http://en.wikipedia.org/wiki/Neural_network
* http://en.wikipedia.org/wiki/Artificial_neural_network
* http://www.cs.stir.ac.uk/~lss/NNIntro/InvSlides.html
* http://www.willamette.edu/~gorr/classes/cs449/intro.html
* http://www.psych.utoronto.ca/users/reingold/courses/ai/nn.html
* http://www.doc.ic.ac.uk/~nd/surprise_96/journal/vol4/cs11/report.html
* http://www.learnartificialneuralnetworks.com/#Intro
* http://www.ibm.com/developerworks/library/l-neural/
* http://www.ai-junkie.com/ann/evolved/nnt1.html
* http://www.heatonresearch.com/course/intro-neural-nets-cs
* http://www.codeproject.com/KB/recipes/NeuralNetwork_1.aspx
* http://www.codeproject.com/KB/recipes/brainnet.aspx
== Vehicle control ==
* http://www.wired.com/medtech/health/news/2004/10/65438
* [http://mmi.tudelft.nl/pub/patrick/Liang.Q-CGAIDE2004.pdf TOWARDS A NEURAL CONTROL ARTIFICIAL PILOT]
* [http://www.kbs.twi.tudelft.nl/Publications/Conference/2002/Ehlert.P.A.M-GAMEON2002.html Recognising situations in a flight simulator environment]
* [http://soar.wichita.edu/dspace/handle/10057/883 Damage tests on an adaptive flight control system]
* [http://www.neurones.espci.fr/Articles_PS/rivals2.pdf MODELING AND CONTROL OF MOBILE ROBOTS AND INTELLIGENT VEHICLES]
* http://freespace.virgin.net/michael.fairbank/neuropilot/

Revision as of 08:07, 4 October 2011

Status: WIP/draft

Last update: 10/2011

Author/s: Hooray

topics to be covered

  • pre-requisites (matrix maths)
  • What are neural networks?
  • advantages and disadvantages
  • use cases in FlightGear (AI, bombable, combat etc)
  • model of an artificial neuron
    • number of 1-n inputs
    • each input has one associated weight (positive/negative floating point factor)
    • computation of activation value (foreach input)
    • activation threshold
    • output signal
  • layering neural networks (input layer, processing layers, output layer)
  • types of networks
    • feedforward network
  • backpropagation
  • training a network
  • types of NN training
  • Implementing Neural Networks (NN) in Nasal
    • using vectors of inputs and associated input weights
    • using a Nasal hash as a helper object
  • Mapping properties to neural inputs
  • Mapping neural network outputs to properties


Links

Vehicle control