A neural network consists of large number of processors and they are arranged in form of tiers. The first tier receives raw input which is processed and passed on to the second tier. The output of first tier will be the input to the second tier, the last tier produces the system output.
Each processing node has its own small sphere of knowledge, including what it has seen and any rules it was originally programmed with or developed for itself. The tiers are highly interconnected, which means each node in tier n will be connected to many nodes in tier n-1-- its inputs -- and in tier n+1, which provides input for those nodes. There may be one or multiple nodes in the output layer, from which the answer it produces can be read.
Neural networks are notable for being adaptive, which means they modify themselves as they learn from initial training and subsequent runs provide more information about the world. The most basic learning model is centered on weighting the input streams, which is how each node weights the importance of input from each of its predecessors. Inputs that contribute to getting right answers are weighted higher.