We can define even and odd functions either by using the graph or the algebraic conditions. We will use the algebraic conditions when two even functions or two odd functions or one even and one odd function are
2, residual connection and layer nor- malization (LN) would be conducted after TD-MHSA. Spatio-temporal feed-forward. The vanilla feed-forward network consists of two linear transformation layers, where the hidden dimension D′ between two layers is ...