Question 2 a) Compare and contrast the goals in Linear Regression and Logistic Regression.

b) The form of a linear regression model is y=wTx. Assuming the mean squared error cost function, derive gradient descent updates for the weights w.

c) What is the limitation of the networks without hidden layers, that was overcome by Multilayer Networks? Is it is essential that the activation function is non-linear?

d) Practical pitfalls with training neural networks include: (i) getting stuck in local optima, (ii) underfitting or overfitting, (iii) bad learning rate. Explain what each of these means.