What is an Artificial Neural Network?
Artificial Neural Networks (ANNs) are computer models inspired by the workings of animal brains. They consist of collections of nodes, commonly referred to as neurons, which are connected in a graph.
Neurons are typically arranged in layers, performing different transformations on their inputs. The first layer is known as the input layer, and the last is the output layer.
The connections between neurons are known as edges, and signals can be transmitted along these to other neurons. Signals are real numbers, and they may traverse layers more than once.
Neurons that receive signals process them, and may in response send signals to other neurons to which they are connected to them. When a signal is outputted by a neuron, it is a nonlinear function of the sum of its inputs.
Neurons and edges typically have weights that adjust as learning proceeds. Weights increase or decrease the strength of the signal at a connection.
Neurons may have thresholds such that signals are transmitted onwards only if the aggregate strength of a signal is greater than them.