Chapter Summary

    In this chapter, you learned how a feedforward backpropagation neural network functions. The feedforward backpropagation neural network is actually composed of two neural network algorithms. It is not necessary to always use feedforward and backpropagation together, but this is often the case. Other training methods will be introduced in coming chapters. The term “feedforward” refers to a method by which a neural network recognizes a pattern. The term “backpropagation” describes a process by which the neural network will be trained.

    A feedforward neural network is a network in which neurons are only connected to the next layer. There are no connections between neurons in previous layers or between neurons and themselves. Additionally, neurons are not connected to neurons beyond the next layer. As a pattern is processed by a feedforward design, the thresholds and connection weights will be applied.

    Neural networks can be trained using backpropagation. Backpropagation is a form of supervised training. The neural network is presented with the training data, and the results from the neural network are compared with the expected results. The difference between the actual results and the expected results is the error. Backpropagation is a method whereby the weights and input threshold of the neural network are altered in a way that causes this error to be reduced.

    Backpropagation is not the only way to train a feedforward neural network. Simulated annealing and genetic algorithms are two other common methods. The next chapter will demonstrate how a genetic algorithm can be used to train a neural network.