Alert icon
We're changing our privacy policy. This stuff matters.  Learn more  Dismiss

Neural Net learning the SIN(x)-Function

Loading...

Sign in or sign up now!
Alert icon
Upgrade to the latest Flash Player for improved playback performance. Upgrade now or more info.
10,278
Loading...
Alert icon
Sign in or sign up now!
Alert icon

Uploaded by on Apr 17, 2007

The Neural Net gets trained, to compute the SIN(x)-Function on a common PDA.

Category:

Howto & Style

Tags:

License:

Standard YouTube License

  • likes, 1 dislikes

Link to this comment:

Share to:
see all

All Comments (9)

Sign In or Sign Up now to post a comment!
  • Ok, so it works for ONE period...how about more than one?

    Also what type of "structure" do you use? Feed Forward? is there any neurons feeding their output back to their input?

  • Nice vid!

    I'm trying to do the same in Java, but for some reason the numbers get to big (NaN). I figured that something's wrong with my activation function, i've tried differest functions, but none seem to work...anybody got an idea?

  • There are to many neurons I guess. I tried it with one hidden layer consisting only 5 neurons. It works perfectly with an efficiency of 99.5%

    Oh, I used only training patterns for every 45 degree. The training took about 5sec.

  • also - do u respond to commenters?

  • how many hidden layers did u use? And how many neurons in each layer?

  • so beautiful.. :)

  • what algoritm you use? genetic or back relations?

  • nice

    Which programming language ?

    visual studio c# ?

  • Yeah.. artificial neural networks are pretty amazing

Loading...

Alert icon
0 / 00Unsaved Playlist Return to active list
    1. Your queue is empty. Add videos to your queue using this button:
      or sign in to load a different list.
    Loading...Loading...Saving...
    • Clear all videos from this list
    • Learn more