"Task $1$:

How does the neural network achieve the generalization of knowledge within the training data? Explain with a real$-$life example. $(1$ XL$060$ Marks$)$

What is knowledge distillation? Explain the process of knowledge distillation in neural network with examples. $(10$ Marks$)$

Answer the questions with required text, equations and figures $($must not be directly copied from any source$)"$