Modular Feedforward

As the name indicates, the modular feedforward networks are special cases of MLPs, such that layers are segmented into modules. This tends to create some structure within the topology, which fosters specialization of function in each sub-module. Modular networks are very common in biology.

In contrast to the MLP, modular feedforward networks do not have full interconnectivity between the layers. Therefore, a smaller number of weights are required for the same size network (the same number of PEs). This tends to speed the training and reduce the number of examples needed to train the network to the same degree of accuracy.

Example of a Modular Feedforward Network

NeuroSolutions Home Page