Fundamentals of Machine Learning — Summer 2022

What is machine learning? What are key tasks of machine learning?

Discuss candidate-elimination algorithm.

Compare Supervised, Unsupervised and Semi supervised Learning.

Define following terms in decision tree. 1) Leaf node 2) Entropy 3) Information gain

Briefly explain the properties of Gini Impurity in decision tree.

List down the advantages of the Decision Trees.

List out the disadvantages of the Decision Trees.

If it takes one hour to train a Decision Tree on a training set containing 1 million instances, roughly how much time will it take to train another Decision Tree on a training set containing 10 million instances?

Why do we require Pruning in Decision Trees? Explain.

Describe the structure of an artificial neuron. How is it similar to a biological neuron? What are its main components?

What is threshold activation function in ANN?

Design a multi-layer perceptron to implement A XOR B.

Describe, in details, the process of adjusting the interconnection weights in a multi-layer neural network.

Explain the concept of Prior, Posterior, and Likelihood with an example.

Discuss application of ANN in face recognition.

Explain, in details, the backpropagation algorithm. What are the limitations of this algorithm?1

What is Naïve Bayes classifier? Why is it named so?

Briefly explain optimal Bayes classifier.

Adrug test (random variable T) has 1% false positives (i.e., 1% of those not taking drugs show positive in the test), and 5% false negatives (i.e., 5% of those taking drugs test negative). Suppose that 2% of those tested are taking drugs. Determine the probability that somebody who tests positive is actually taking drugs (random variable D).

Explain Minimum Description Length Principle.

Write two strength and weakness of Bayesian classifier.

Explain how Naïve Bayes classifier is used in text classification.

Explain overfitting and underfitting.

Discuss a scenario of banking system where machine learning can be helpful.

What are Bayesian Belief networks? Where are they used? Can they solve all types of problems?