Skip to content
  • Categories
  • Recent
  • Tags
  • Popular
  • World
  • Users
  • Groups
Skins
  • Light
  • Cerulean
  • Cosmo
  • Flatly
  • Journal
  • Litera
  • Lumen
  • Lux
  • Materia
  • Minty
  • Morph
  • Pulse
  • Sandstone
  • Simplex
  • Sketchy
  • Spacelab
  • United
  • Yeti
  • Zephyr
  • Dark
  • Cyborg
  • Darkly
  • Quartz
  • Slate
  • Solar
  • Superhero
  • Vapor

  • Default (No Skin)
  • No Skin
Collapse
Code Project
  1. Home
  2. General Programming
  3. C / C++ / MFC
  4. Neural Network Function Estimation

Neural Network Function Estimation

Scheduled Pinned Locked Moved C / C++ / MFC
questionsysadmintutorial
1 Posts 1 Posters 0 Views 1 Watching
  • Oldest to Newest
  • Newest to Oldest
  • Most Votes
Reply
  • Reply as topic
Log in to reply
This topic has been deleted. Only users with topic management privileges can see it.
  • A Offline
    A Offline
    Alex H 1983
    wrote on last edited by
    #1

    Hello every one, I have one question regarding neural networks and it's functionality. I'm newbie in this field. Actually i want to use a supervised neural network to estimate a function values at different locations. Suppose we want to estimate y = x^2 and we have some training data to learn the network x=1 => y=1 x=2 => y=4 x=3 => y=9 x=4 => y=16 x=5 => y=25 Now suppose we want to estimate function value at x = 10 At first it seems that Back propagation is the best network for this purpose but after i tried some source code from CodeProject i found out that Back Propagation can only estimate function values that are around the training set!(Tell me if I'm wrong!) so for example it can estimate function at x=4.5 but it cannot estimate function at x=10 (i think it will return 25) So which type of Neural Network should i use for this purpose? Any ideas?

    1 Reply Last reply
    0
    Reply
    • Reply as topic
    Log in to reply
    • Oldest to Newest
    • Newest to Oldest
    • Most Votes


    • Login

    • Don't have an account? Register

    • Login or register to search.
    • First post
      Last post
    0
    • Categories
    • Recent
    • Tags
    • Popular
    • World
    • Users
    • Groups