Yeah, you are right. I also think it must be the online part of the algorithm.
On Fri, Dec 4, 2009 at 9:45 PM, Ted Dunning <[email protected]> wrote: > You are correct that only a little bit of A'A is used for any given user's > recommendation, but it is the columns that correspond to their history, not > the rows. This doesn't matter much to get this wrong if A'A is still > symmetrical, but getting it right can make your code less confusing for > others and if you limit the number of non-zero elements in each row of A'A, > then it becomes important to keep track of which is which. > > On Fri, Dec 4, 2009 at 12:57 AM, Gökhan Çapan <[email protected]> wrote: > > > ith row of the matrix A'A contains all items and their similarity degrees > > to > > the item that is represented at ith column of the matrix A. > > I guess it is enough using only a subset of A'A at the final step, that > is, > > the rows which represent the items that are in active user's history. > > btw, I also want to contribute to that implementation, if we can decide > the > > algorithm. > > > > -- > Ted Dunning, CTO > DeepDyve > -- Gökhan Çapan
