Question 1
Why is a Deep Belief Network not a Boltzmann Machine ?
Question 2
Brian looked at the direction of arrows in a DBN and was surprised to find that the data is at the "output". "Where is the input ?!", he exclaimed, "How will I give input to this model and get all those cool features?" In this context, which of the following statements are true? Check all that apply.
Question 3
Suppose you wanted to learn a neural net classifier. You have data and labels. All you care about is predicting the labels accurately for a test set. How can pretraining help in getting better accuracy, even though it
does not use any information about the labels ?
Question 4
Why does pretraining help more when the network is deep ?
Question 5
The energy function for binary RBMs goes by
E(v,h)=−∑ivibi−∑jhjaj−∑i,jviWijhj
When modeling real-valued data (i.e., when
v
is a real-valued vector not a binary one) we change it to
E(v,h)=∑i(vi−bi)22σ2i−∑jhjaj−∑i,jviσiWijhj
Why can't we still use the same old one ?