Fundamentals of Machine Learning 2018 Question Paper — Government Col…
The 2018 Fundamentals of Machine Learning previous year question paper (Government College of Engineering and Technology, Jammu), with every question and its marks.
- University: Government College of Engineering and Technology, Jammu
- Subject: Fundamentals of Machine Learning
- Course: MACHINE LEARNING
- Branch: Computer Engg.
- Year: 2018
- Paper: end-term
- Duration: 180 minutes
- Total marks: 100
Instructions
- Attempt five questions in all, selecting at least two questions from each section.
Questions
SECTION - A
- QQ1.(a). What are the important objectives of machine learning? Discuss different important examples of machine Learning. [10 marks]
- Q(b). Explain the various classifier performance measures (accuracy, precision, recall, sensitivity, specificity, ROC curve). [10 marks]
- QQ2.(a). What are the advantages and limitations of Locally weighted Linear Regression? [10 marks]
- Q(b). Describe k-nearest neighbor algorithm. Why is it called instance based learning? [10 marks]
- QQ3.(a). What is the goal of Support Vector Machine (SVM)? How to compute the margin? [10 marks]
- Q(b). What is Hierarchical clustering? Consider the following distance matrix and apply hierarchical clustering to cluster the objects u, v, w, x, y u v w x y u 0 1 2 2 3 v 1 0 2 4 3 w 2 2 0 1 5 x 2 4 1 0 3 y 3 3 5 3 0 [10 marks]
- QQ4.(a). What is the difference between classification and clustering? State and explain various techniques used for clustering. [10 marks]
- Q(b). Given that the Observations are already clustered in two clusters C1 and C2 as shown in the table. Cluster C1: Obs. X1 X2 A 2 4 B 8 2 D 1 5 Cluster C2: Obs. X1 X2 C 9 3 E 8.5 1 Apply K-mean clustering algorithm to find and plot initial and final distribution of observations in C1 and C2. [10 marks]
SECTION - B
- QQ5.(a). Define (i) Prior Probability (ii) Conditional Probability (iii) Posterior Probability [10 marks]
- Q(b). Describe the Naive Bayesian method of classification. What assumptions does this method make about the attributes and the classification? [10 marks]
- QQ6.(a). Describe in brief : 1) Hypothesis space search in decision tree 2) Inductive bias in decision tree learning [10 marks]
- Q(b). Give decision trees to represent the following boolean functions: (a) A $\land$ $\sim$B (b) A $\lor$ [B $\land$ C] (c) A XOR B (d) [A $\land$ B] $\lor$ [C $\land$ D] [10 marks]
- QQ7. State the Bayes Rule and explain how it is applied to pattern classification problems. Show that in a multiclass classification task the Bayes decision rule minimizes the error probability. [20 marks]
- QQ8.(a). Discuss the learning tasks and Q learning in the context of reinforcement learning. [10 marks]
- Q(b). Write note on Random Forest Algorithm. [10 marks]