Types of propagation:

1. What is forward propagation?

Forward propagation means all those processes happen in our neural network to predict a value. We know that for prediction first, we multiply weights and inputs and then do sum all of them and then add a bias. After this, we apply an activation function. This process happens in all the neurons from hidden layers to output layers. To do this process we move from the left side to the right side means first input layer then hidden layers and output layer. It means we are going forward direction. After completing this process we get an output. Together all these processes are called forward propagation. In forward propagation we can't come back or do process in backward direction. We can only move forward.

2. What is Back propagation?

Back-propagation happens after forward propagation. After forward propagation, we get an output. After getting the output we calculate loss and our work is to reduce the loss as much as possible by updating the weights. All processes to reduce loss come in back-propagation. This process is called back-propagation because all the process is done in the backward direction. In back-propagation process starts from the output layers, then hidden layers, and then the input layer. In this process, our target is to update weights by using an optimizer to reduce loss.