An artificial neural network is a collection of simple interconnected algorithms that process information in response to external input. This neural net is loosely modeled after biological neural networks.
The ANN model is organized in layers, each one made up of interconnected nodes. The input layer communicates with one or more hidden layers. Here, the nodes take the weighted connections and use an activation function to pass their signal to the output layer.
An artificial neural network incorporates a way of learning, of which there are many, that essentially modifies the weights of the connections. In this way, it learns by example.
One type, known as back propagation, is a supervised learning process. The neural net is presented with a pattern and guesses what it is. Then it determines how far its guess was from the actual answer and adjusts the connection weights as required.