Generalized feedforward networks are a special case of multilayer perceptrons such that connections can jump over one or more layers. In theory, a MLP can solve any problem that a generalized feedforward network can solve. In practice, however, the generalized feedforward networks often solve the problem much more efficiently. The advantage of the generalized FF network is in its ability to project activities forward by bypassing layers. The result is that the training of the layers closer to the input become much more efficient.
