Artificial Neural Network

                                               The neural networks that are increasingly being used in artificial intelligence research mimic those found in the nervous systems of vertebrates. The main characteristic of these (top) is that each neuron, or nerve cell, receives signals from many other neurons, through its branching dendrites. It produces an output signal that depends on the values of all the input signals, and passes this output on to many other neurons along a branching fibre called an axon. In an artificial neural network (bottom), input signals, such as signals from a television camera’s image, fall on a layer of input nodes, or computing units. Each of these is linked to several other nodes, which, being intermediate between the input and output nodes of the network, are called “hidden” nodes. Each hidden node performs a calculation on the signals reaching it, and sends a corresponding output signal to further nodes. The final output is a highly processed version of the input. Artificial neural networks can be rapid, and can “learn” to perform more and more accurately without needing to be explicitly programmed.