Neural networks are loosely analogous to neurons.  Neural networks have nodes, layers, and synapses instead of dendrites, axons, and somas.  The weights that are assigned to individual synapse are the network’s equivalent to a neuron’s neurotransmitters.  From a top-down structural description, a neural network consists of four main areas- the input-layer, hidden-layer, output-layer, and synapses-space.  Each layer is comprised of a group of similar nodes- input-nodes, hidden-nodes, and output-nodes.  The area between layers is referred to as the synapse-space.  The individual connections between layer nodes lie within the synapse-space.  In a three-layered network, there would be two synapse-spaces.  The first synapse-space would contain the connections between the input-nodes and the hidden-nodes.  The second synapse-space would house the connections between the hidden-nodes and the output-nodes. [Graci]
 

    Below is a pictorial representation of a 3-layered neural network.


 
 

       "Neural networks were initially studied by computer and cognitive scientists in the late 1950s and early 1960s in an attempt to model sensory perception in biological organisms. Neural networks have been applied to many problems since they were first introduced, including pattern recognition, handwritten character recognition, speech recognition, financial and economic modeling, and next-generation computing models." [encarta 99]
A neural network can be either feed-forward only or have the ability to backtrack.  Feed-forward networks are relatively simple to understand.  Information is passed in a straight-forth manner from one node to its connecting node.  At each juncture a threshold is either reached and the data continues on to its connecting node, or the threshold is not reached; thus the connecting node receives a null value which prevents that node from being activated.  However, in a network that is able to backtrack, receiving nodes are able to send back to its preceding node the result it has been sent.  This allows a hidden-node (hidden-cell) the ability to return a value that does not met its threshold back to its connecting input-node.  The input-node can then try sending the data along its connection paths to an alternative node. [Graci]

    Nodes may be either discrete or continuous. "Discrete nodes send an output signal of 1 if the sum of received signals is above a certain critical value called a threshold value, otherwise they send an output signal of 0. Continuous nodes are not restricted to sending output values of only 1s and 0s; instead they send an output value between 1 and 0 depending on the total amount of input that they receive—the stronger the received signal, the stronger the signal sent out from the node and vice-versa.  Continuous nodes are the most commonly used in actual artificial neural networks." [Encarta 99]

    Neural networks first go through a training phase where the network establishes the associated weight between each connection.  This is done by first inputting a data set with known output results.  After each trial, the weights are slightly adjusted until the network produces 100% accuracy.  After the network has been trained it is then ready to be placed into production to be used in application procedures with unknown answers. [Graci]