The front end.
1 post • Page 1 of 1
What is the difference in learning the parameters for DBN in an unrolled and in a non-unrolled network? Does the process of learning the parameters in a non-unrolled network use the records from all time slices included in the dataset, and if so how are they combined? For example assuming three time slices, to learn the probability P(At|At-1), how will the values P(A2|A1), P(A1|A0) be compiled?