Answer:
The back propagation algorithm causes the network to settle into a stable state where it can correctly respond, to any desired degree of accuracy, to all inputs in the training set.
Step-by-step explanation:
Back propagation algorithm is a part of the learning of a neural network. In a simple neural network setting at each iteration;
- The network assumes random weights at each network layer and passes the value to the next trough an activation function.
- Then a loss function is calculated by comparing the distace of the final value with the label value using a predetermined distance metric.
- The weights are optimized trough back propagation
Thus, back propagation algorithm used to reach the final weights of the neural network, so that it can work more accurately.