Artificial Intelligence and Machine Learning — DU B. Sc. (Hons) Electronics Previous Year Question Papers

Machine Learning 2. There are seven questions in all, out of which you e to attempt five questions. 1. (a) Define a rational agent in the context of Al, How does it differ from a human agent? (b) What are Uninformed search strategies? (c) Define the PEAS representation for a medical diagnostic system. (d) What is expert system? Write its characteristics. (e) Distinguish between overfitting and underfitting. How it can affect model generalization? (t) What is the difference between agglomerative and divisive hierarchical clustering? 2. (a) What is knowledge-based agent? Explain is role and importance. (b) Enumerate Classical "Water jug Problem". Describe the state space for this problem and also give the solution. (c) How do the Cognitive Modelling Approach and the Laws of Thought Approach differ in their methodologies for developing Al systems? 3. (a) For the given search graph determine the optimum path from A to G using (i) Uniform Cost Search where the numbers on the links are link costs and the numbers next to the states are heuristic estimates. Note that the ares are undirected. Is the heuristic given in the problem admissible and consistent? Explain. (b) What is the difference between a deterministic and a stochastic environment in Al? Is a chess game played between two Al systems a deterministic or stochastic environment? Explain your answer. (c) Explain the following terms - (Ill) Autonomy (9+6+3) (a) What is Depth Limited Search (DLS) and Iterative Deepening Depth First Search (IDFFS)? How are they different from Depth First Search? Give the time and space complexities of DLF and (b) Determine the path-traversal for the given graph to move from initial state A using : (i) Breadth First Search (il) Depth First Search (c) A salesman needs to visit 4 cities and return to the starting point. The distance between the cities is known, and the goal is to find the shortest possible route that visits each city exactly once and returns to the starting point. The distance matrix (in kilometres) between the cities is given as (a) A robotic vacuum cleaner moves between three rooms in a house: RI: Living Room The movement of the vacuum cleaner is modelled as a Markov Chain with the following transition matrix P where Py, represents the probability of transitioning from room R, to room Rj. Suppose the vacuum cleaner starts in the Living Room (R,). Calculate the joint probability that the vacuum cleaner will be in the Living Room at time t=0, the Kitchen at time t=1, and the Bedroom at time t=2. (b) What is policy iteration? How does it differ from value iteration? (c) A witness in a hit-and-run accident identifies a taxi as being blue. There are two taxi companies: 85% of taxis are green, and 15% are blue. The witness is 80% accurate in identifying the correct colour of the taxi. Use Bayes' Theorem to determine the probability that the taxi is actually blue, given the witness's statement? (9+6+3) 6. (a) For the given game tree