The fundamental unit of the neural network is

The fundamental unit of the neural network is the neuron, also known as a node or perceptron.

Here are the steps that describe how it works:

1. Input Layer: Each neuron in the neural network receives some inputs. These inputs can be feature values in the case of the input layer.

2. Weights Assignment: Each of these inputs is given a weight which can be thought of as its importance in the prediction. More the weight of an input, more it will have an influence on the output.

3. Summation and Bias Addition: All the weighted inputs are then added together with a bias value. The bias value allows us to shift the activation function to the left or right, which may be critical for successful learning.

4. Activation Function: The result of the summation is passed through an activation function. The activation function is used to introduce non-linearity into the output of a neuron. This is important because most real world data is non linear and we want neurons to learn these non linear representations.

5. Output Layer: Every neuron's output can then serve as input to the neurons of the next layer, which could be a hidden layer or the output layer of the neural network.

This process is repeated for every neuron in the hidden layers of the neural network. The final layer is the output layer which gives the final prediction/classification.