Get the entire book!

In the previous chapter you learned about the feed forward back propagation neural network. While feed forward neural networks are very common, they are not the only architecture for neural networks. In this chapter we will examine another very common architecture for neural networks.

The Kohonen neural network contains no hidden layer. This network architecture is named after its creator, Tuevo Kohonen. The Kohonen neural network differs from the feedfroward back propagation neural network in several important ways. In this chapter we will examine the Kohonen neural network and see how it is implemented. Chapter 7 will continue by showing a practical application of the Kohonen neural network, optical character recognition.