Chapter Summary

    Computers can process information considerably faster than human beings. Yet, a computer is incapable of performing many of the same tasks that a human can easily perform. For processes that cannot easily be broken into a finite number of steps, a neural network can be an ideal solution.

    The term neural network typically refers to an artificial neural network. An artificial neural network attempts to simulate the biological neural networks contained in the brains of all animals. Artificial neural networks were first introduced in the 1950’s and through the years of their development have experienced numerous setbacks; they have yet to deliver on the promise of simulating human thought.

    Neural networks are constructed of neurons that form layers. Input is presented to the layers of neurons. If the input to a neuron is within the range that the neuron has been trained for, then the neuron will fire. When a neuron fires, a signal is sent to the layers of neurons to which the firing neuron is connected. The connections between neurons are called synapses. Java can be used to construct such a network.

    Neural networks must be trained and validated. A training set is usually split in half to provide both a training and validation set. Training the neural network consists of running the neural network over the training data until the neural network learns to recognize the training set with a sufficiently low error rate. Validation occurs when the neural network’s results are checked.

    Just because a neural network can process the training data with a low rate of error, does not mean the neural network is trained and ready for use. Before the neural network is placed into production use, it must be validated. Validation involves presenting the validation set to the neural network and comparing the actual results produced by the neural network with the anticipated results.

    The neural network is ready to be placed into production if, at the end of the validation process, the results from the validation run meet a satisfactory error level. If the results are not satisfactory, then the neural network will have to be retrained before it can be placed into production.

    Neural networks are comprised of many neurons. Their threshold and weight values are combined into weight matrixes. A weight matrix is stored in a regular mathematical matrix. Chapter 2 will introduce several Java classes designed to store matrix values and perform matrix mathematics. The neural networks in this book will be built upon these matrix classes.