I want to program NN with many outputs, how many outputs is limit for NN? if output number is large, what is the relationship between traning data and outputs?
thanks
0
Limit for output numbers?
Started by truongthinhs, Jan 09 2008 01:59 PM
2 replies to this topic
#2
-
- Members
-
- 368 posts
Senior Member
Posted 09 January 2008 - 02:59 PM
Homework ?
Also, your question is quite difficult to understand, and very inexact.
Basically, you can have an arbitrary number of outputs for your neuronal net, you are only limited by memory and processor speed.
If, by output, you mean what classification can be done with a given neural net, this also is solvable only if you give the appropriate activation function, and the depth of the net.
Generally, for the relation between training data and outputs, the larger your neuronal net is and the more clusters you want to seperate, the more training data is required.
Cheers,
- Wernaeh
Also, your question is quite difficult to understand, and very inexact.
Basically, you can have an arbitrary number of outputs for your neuronal net, you are only limited by memory and processor speed.
If, by output, you mean what classification can be done with a given neural net, this also is solvable only if you give the appropriate activation function, and the depth of the net.
Generally, for the relation between training data and outputs, the larger your neuronal net is and the more clusters you want to seperate, the more training data is required.
Cheers,
- Wernaeh
Some call me mathematician, some just call me computer guy. Yet, I prefer the term professional weirdo :)
#3
-
- Members
-
- 10 posts
New Member
Posted 10 January 2008 - 02:12 AM
Thank Wernaeh for your information!
1 user(s) are reading this topic
0 members, 1 guests, 0 anonymous users
