Great! We have come a long way, from looking at the biological neuron, to the types of neuron, to determining accuracy, and correcting the learning of the neuron. Only one question remains: how can the whole network of neurons learn together?

Backpropagation is an incredibly smart approach to making gradient descent happen throughout the network across all layers. Backpropagation leverages the chain rule from calculus to make it possible to transfer information back and forth through the network:

In principle, the information from the input parameters and weights is propagated through the network to make a guess at the expected output and then the overall inaccuracy is backpropagated through the layers of the network so that the weights can be adjusted and the output can be guessed again.

This single cycle of learning is called a training step or iteration. Each iteration is performed on a batch of the input training samples. The number of samples in a batch is called batch size. When all of the input samples have been through an iteration or training step, then it is called an epoch.

For example, let's say there are 100 training samples and in every iteration or training step, there are 10 samples being used by the network to learn. Then, we can say that the batch size is 10 and it will take 10 iterations to complete a single epoch. Provided each batch has unique samples, that is, if every sample is used by the network at least once, then it is a single epoch. 

This back-and-forth propagation of the predicted output and the cost through the network is how the network learns.

We will revisit training step, epoch, learning rate, cross entropy, batch size, and more during our hands-on sections.