ABSTRACT
Neural networks offer a mathematical model that attempts to mimic the human brain. Knowledge is often represented as a layered set of interconnected processors. Neural network learning can be supervised or unsupervised. Learning is accomplished by modifying network connection weights while a set of input instances is repeatedly passed through the network. This chapter discusses two methods for training feed-forward networks and one technique for unsupervised neural net clustering. The feed-forward neural network architecture is commonly used for supervised learning. Feed-forward neural networks contain a set of layered nodes and weighted connections between nodes in adjacent layers. Feed-forward neural networks are often trained using a backpropagation learning scheme. Backpropagation learning works by making modifications in weight values starting at the output layer and then moving backward through the hidden layers of the network. Genetic learning can also be applied to train feed-forward networks. The self-organizing Kohonen neural network architecture is a popular model for unsupervised clustering.
