Perceptron is a single layer NN, hence it has no hidden layer.
In the late 80s to early 90s, we have seen many developments in NNs. New NN structures such as: the radial basis function network , bidirectional associative memories , B-splines network , digital neurocomputer , functional-link networks , knapsack packing networks  and wavelet networks  were proposed. Different combinations of network topologies to improve the rep-resentational structure, such as recurrent backpropagation which combines feedback and feedforward topologies, were explored [3, 188, 240].
Figure 3.2: The basic elements of neural networks.