Machine learning Question bank and notes

Machine Learning (15cs73)

Module 1

Module 2

1.Why prefer short hypotheses?
2.Discuss issues in decision tree learning.
3. Explain the capabilities and limitations of ID3 in terms of search space and search strategy
4. Discuss restriction bias and Preference Bias
5. Describe ID3 algorithm
6. Illustrate the ID3 algorithm for training examples given in table below. Here the target attribute is play. Draw the complete decision tree.

Module 3

1.Explain in detail perceptron based ANN system its representation and training rule

2.Explain Backpropagation algorithm
3.Explain appropriate problems for Neural Network Learning with its characteristics
4.Explain the derivation of gradient descent rule
5.Write and explain gradient descent algorithm for training a linear unit.
6.Explain the differentiable sigmoid threshold unit

Module 4- Bayesian Learning

Bayesian Learning (Chapter 6)
1. Define (i) Prior Probability (ii) Conditional Probability (iii) Posterior Probability
2. Define Bayesian theorem? What is the relevance and features of Bayesian theorem? Explain the practical difficulties of Bayesian theorem.
3. Consider a medical diagnosis problem in which there are two alternative hypotheses: 1. That the patient has a particular form of cancer (+) and 2. That the patient does not (-). A patient takes a lab test and the result comes back positive. The test returns a correct positive result in only 98% of the cases in which the disease is actually present, and a correct negative result in only 97% of the cases in which the disease is not present. Furthermore, .008 of the entire population have this cancer. Determine whether the patient has Cancer or not using MAP hypothesis.
4. Explain Brute force Bayes Concept Learning
5. Define MAP hypothesis. Derive the relation for hMAP using Bayesian theorem.
6. What are Consistent Learners?
7. Discuss Maximum Likelihood and Least Square Error Hypothesis.
8. Describe Maximum Likelihood Hypothesis for predicting probabilities.
9. Describe the concept of MDL. Obtain the equation for hMDL
10. What is conditional Independence?
11. Explain Naïve Bayes Classifier with an Example.
12. Explain the Gradient Search to Maximize Likelihood in a neural Net.
13. What are Bayesian Belief nets? Where are they used?
14. Explain Bayesian belief network and conditional independence with example.
15. Explain the concept of EM Algorithm. Discuss what are Gaussian Mixtures.

MODULE 5

EVALUATING HYPOTHESIS, INSTANCE BASED LEARNING, REINFORCEMENT LEARNING

1. Explain the two key difficulties that arise while estimating the Accuracy of Hypothesis.
2. Define the following terms
a. Sample error b. True error c. Random Variable d. Expected value e. Variance f. standard Deviation
3. Explain Binomial Distribution with an example.
4. Explain Normal or Gaussian distribution with an example.
5. Suppose hypothesis h commits r = 10 errors over a sample of n = 65 independently drawn examples.

What is the variance and standard deviation for number of true error rate errorD(h)?
What is the 90% confidence interval (two-sided) for the true error rate?
What is the 95% one-sided interval (i.e., what is the upper bound U such that errorD(h) ≤5 U with 95% confidence)?
What is the 90% one-sided interval?

6. What are instance based learning? Explain key features and disadvantages of these methods.
7. Explain the Knearest neighbour algorithm for approximatin a discrete – valued function
8.Describe K-nearest Neighbour learning Algorithm for continues (real) valued target function.
9. Discuss the major drawbacks of K-nearest Neighbour learning Algorithm and how it can be corrected
10. Define the following terms with respect to K - Nearest Neighbour Learning :
i) Regression ii) Residual iii) Kernel Function.
11. Explain Locally Weighted Linear Regression.
12. Explain radial basis function
13. Explain CADET System using Case based reasoning.
14. What is Reinforcement Learning and explain Reinforcement learning problem with neat diagram.
15. Write Reinforcement learning problem characteristics.
16. Explain the Q function and Q Learning Algorithm assuming deterministic rewards and actions with example.