/  Deep Learning Interview questions and answers   /  How do Neural Networks update weights and Biases during Back Propagation?
Deep learning 31 (i2tutorials)

How do Neural Networks update weights and Biases during Back Propagation?

Ans. To reduce the error by changing the values of weights and biases.

calculate the rate of change of error w.r.t change in weight.

Deep learning 34 (i2tutorials)

Since we are propagating backwards, first thing we need to do is, calculate the change in total errors w.r.t the output O1 and O2.

Deep learning 35 (i2tutorials)

Now, we will propagate further backwards and calculate the change in output O1 w.r.t to its total net input.

Deep learning 36 (i2tutorials)

Let’s see now how much does the total net input of O1 changes w.r.t  W5?
Deep learning 37 (i2tutorials)

Step – 3: Putting all the values together and calculating the updated weight value

Now, let’s put all the values together:

Deep learning 38 (i2tutorials)

Let’s calculate the updated value of W5:

Deep learning 39 (i2tutorials)

This is an example to know how to update the weights and biases in Neural Network. This process continues until we get minimized error.

Leave a comment