Jump to content
  • Advertisement
Sign in to follow this  
johnnyBravo

Some more feedforward backprobagation network questions

This topic is 4769 days old which is more than the 365 day threshold we allow for new replies. Please post a new topic.

If you intended to correct an error in the post then please contact us.

Recommended Posts

Hey I've got a couple of feed forward backprobagation network questions. Say you want to train the network to 2 input/desiredOutput vectors. Would you train the network to one of the vectors until the weights stablize, and then do the same for the next set of vectors. Then you repeat the whole process until all the weights have stablized? Also does more neurons in the hidden layer mean the larger range of input/desiredOutput vectors that can be trained into the network? And also what would adding more hidden layers do, would it also allow the larger range of input/desiredOutput vectors to be trained? Thankyou.

Share this post


Link to post
Share on other sites
Advertisement
Sign in to follow this  

  • Advertisement
×

Important Information

By using GameDev.net, you agree to our community Guidelines, Terms of Use, and Privacy Policy.

We are the game development community.

Whether you are an indie, hobbyist, AAA developer, or just trying to learn, GameDev.net is the place for you to learn, share, and connect with the games industry. Learn more About Us or sign up!

Sign me up!