A neuron is a computational unit in a neural network that combines input values with learned weights and applies an activation function. Neurons are arranged in layers and pass signals to later layers so that the network can learn increasingly useful representations.
In machine learning, a distinct unit within a hidden layer of a neural network. Each neuron performs the following two-step action: 1. Calculates the weighted sum of input values multiplied by their corresponding weights. 2. Passes the weighted sum as input to an activation function. A neuron in the first hidden layer accepts inputs from the feature values in the input layer. A neuron in any hidden layer beyond the first accepts inputs from the neurons in the preceding hidden layer. For example, a neuron in the second hidden layer accepts inputs from the neurons in the first hidden layer. The following illustration highlights two neurons and their inputs. !A neural network with an input layer, two hidden layers, and an output layer. Two neurons are highlighted: one in the first hidden layer and one in the second hidden layer. The highlighted neuron in the first hidden layer receives inputs from both features in the input layer. The highlighted neuron in the second hidden layer receives inputs from each of the three neurons in the first hidden layer. A neuron in a neural network mimics the behavior of neurons in brains and other parts of nervous systems.