Artificial neural network
Jump to navigation
Jump to search
Artificial Neural Network (ANN for short) is a processing model inspired on the biological neural networks. Artificial neural networks are composed by simple nodes called artificial neuron and the processing behavior is stored in the node interconnections as weights.
Adaptation and Learning
When a neuron receives and processes an input signal, it changes its behavior by changing its threshold and/or weight values, producing also a change in the entire network. Since artificial neurons have a predictable behavior, artificial neural networks can be trained by being fed with sequences of inputs, often determined by certain functions. Besides, there are neural networks which do not require training.