View Single Post
  #3  
Old 05-13-2013, 01:57 PM
Moobb Moobb is offline
Junior Member
 
Join Date: Apr 2013
Posts: 9
Default Re: Question 9 - minimum # of weights

In the lecture on neural networks it is mentioned that the number of weights works as a reference for the VC dimension of the network. Linking to this question, is there any guidance towards how to construct a neural net? I am thinking about the balance between the number of hidden layers and the number of units per layer. My intuition is that working with units near to equally distributed across the layers increases the VC dimension, so more expressiveness against larger generalasation error? In practice one would then decide based on a generalisation error analysis?
Reply With Quote