Improved backpropagation training algorithm using conic section functions

A new training algorithm composed of a propagation rule which contains MLP and RBF parts to improve the performance of backpropagation is proposed. The network using this propagation rule is known as a conic section function network. This network allows one to convert the open decision boundaries in an MLP to closed ones in an RBF, or vice versa. It reduces the number of centres needed for an RBF and the hidden nodes for an MLP. It is important since this work is aimed at designing a VLSI hardware neural network. Furthermore, it converges to a determined error goal at lower training epochs than an MLP. The performance of an MLP trained backpropagation and also fast backpropagation using adapted learning rates, an RBF net, and the proposed algorithm is compared using Iris plant database. The results show that the introduced algorithm is much better than the others in most cases, in terms of not only training epochs but also the number of hidden units and centres.