The Author Online Book Forums are Moving

The Author Online Book Forums will soon redirect to Manning's liveBook and liveVideo. All book forum content will migrate to liveBook's discussion forum and all video forum content will migrate to liveVideo. Log in to liveBook or liveVideo with your Manning credentials to join the discussion!

Thank you for your engagement in the AoF over the years! We look forward to offering you a more enhanced forum experience.

jiunjiunma (3) [Avatar] Offline
#1
Hi,
I am reading the code for recommendation using SVD (listing 14.3). I understand you are trying to transform the original matrix to a lower-dimension space but why is it calculated as dataMat.T * U [:, :4] * Sig4.I? (Care to help us refreshing our linear algebra?)
Also, the text is referring to a 3-dimensional space (Sig3), but the code is referring a 4-dimension space (Sig4). There seems to be some typos there.

Thanks,
--Jiunjiun
395823 (1) [Avatar] Offline
#2
Hi,
I have the same doubt about the transformed items. Maybe it is a trivial question for someone with high skills in linear algebra, i dont know... but I found that:

representation of itens in latent space = representation of items * V * Sigma.I

I really dont know how to justify xformedItems = dataMat.T * U[:,:4] * Sig4.I

This code is obscure to me. Could someone help me?
Thanks,
Moacyr