ALSO REFFERRED TO AS NEUROMORPHIC systems, artificial intelligence and parallell distributed processing, artificial neural networks (ANN)are an attempt at mimicing the patterns of the human mind. Many researches have concluded that understanding the human mind is probably the most difficult challenge left in science.

In the early 1940's scientists came up with the hypothesis that neurons, fundamental, active cells in all animal nervous systems might be regarded as devices for manipulating binary numbers. Thus spawning the use of computers as the traditional replicants of ANNs.
To be understood is that advancement has been slow. Early on it took a lot of computer power and consequently a lot of money to generate a few hundred neurons. In relation to that consider that an ant's nervous system is composed of over 20,000 neurons and furthermore a human being's nervous system is said to consist of over 100 billion neurons! To say the least replication of the human's neural networks seemed daunting. Today ANNs are being applied to an increasing number of real- world problems of considerable complexity. They are good pattern recognition engines and robust classifiers, with the ability to generalize in making decisions about imprecise input data. They offer ideal solutions to a variety of classification problems such as speech, character and signal recognition, as well as functional prediction and system modeling where the physical processes are not understood or are highly complex (Hassoun, 2000) .

This is a brightly glowing neuron and behind it is the layout for an artficial neural network.

The single cell neuron consists of the cell body, or soma, the dendrites, and the axon. The dendrites receive signals from the axons of other neurons. The small space between the axon of one neuron and the dendrite of another is the synapse. The dendrites conduct impulses toward the soma and the axon conducts impulses away from the soma.The function of the neuron is to integrate the input it receives through its synapses on its dendrites and either generate an action potential or not (Chicurrel, 1995).

Neural Networks use a set of processing elements (or nodes) loosely analogous to neurons in the brain. (Hence the name, neural networks.) These nodes are interconnected in a network that can then identify patterns in data as it is exposed to the data. In a sense, the network learns from experience just as people do. This distinguishes neural networks from traditional computing programs, that simply follow instructions in a fixed sequential order. 

Click on the image above and ask yourself, "Who will be the teacher of the future, man or machine?" 

Now if you will roll your mouse over the picture of the neuron placed above, you will see the basic layout or concept behind artificial neural networks. The bottom layer represents the input layer, in this case with 5 inputs. In the middle is something called the hidden layer, with a variable number of nodes. It is the hidden layer that performs much of the work of the network. The output layer in this case has two nodes, representing output values we are trying to determine from the inputs (Hassoun, 2000).

In truth, the future of ANN's are shady. The secrets of the human mind still escapes us no matter how much we boost the proccessing speed and size. That said, these neural networks have given us incredible advancements in things such as Optical Character Recognition, financial forecasting and even in medical diagnosis. For any group in which a known interrelationship exists with an unknown outcome there is a great possibility that ANN's will be helpful. As long as computer-based training and e-learning courses increase in application, the desire to develop computer systems that can learn by themselves and improve decision-making will be an ongoing goal of information technology.