ivel…mbination of input vectors, weighted by routing coefficients c_ij, determined in the previous step. Intuitively, this means scaling down input vectors and adding them together, which produces output vector s_j. This is done for all higher level capsules.
…a similar way. In a large dataset this has proven to work a lot better than the meta-data approach. Essentially asking people about their behavior is less good compared to looking at their actual behavior. Discussing this further is something for the psychologists among us.
…g. They allow us to capture relationships in language that are very difficult to capture otherwise. However, embedding layers can be used to embed many more things than just words. In my current research project I am using embedding layers to embed online user behavior. In this case I am assigning indices to user behavior like ‘page view on page type X on portal Y’ or ‘scrolled X pixels’. These indices are then used for constructing a sequence of user behavior.