BEU(bihar engineering university) previous year question solution of cse branch . BEU model paper solution.
1. (a) Explain with diagram the organization of a natural language understanding system.
(b) Describe all the levels of language understanding in natural language processing system.
BEU pyq solution is provided below
2. (a) What are agents in AI? How do agents work to import intelligence to a system? Classify the different types of agents and briefly discuss their properties.
(b) Draw the semantic network of the following sentence: Kavita gives a book to her friend.
3. (a) What do you mean by learning? Explain briefly the learning methods. Discuss the advantages and disadvantages of rule-based system.
(b) Explain the human preferences in encoding uncertainty during parsing
4. What is First Order Predicate Logic (FOPL)? Represent the following facts in FOPL: “Anyone passing his Al paper and getting an opportunity to work on live project is Happy. But anyone who studies sincerely or is Lucky can pass all his exams. Ramu did not study but he is Lucky. Anyone who is Lucky gets a live project to work.”
5. Write short notes on the following: 32×4-1
(a) Knowledge
(b) Intelligence
(c) Inheritance knowledge
(d) Knowledge management
6.Describe examples: the following with suitable (a) logistic regression
7. (a) Differentiate between forward chaining and backward chaining. On what factors does the decision to choose forward or backward chaining depend?
(b) Consider the following sentences:
John likes all kinds of food.
- Apples are food.
- Chicken is food.
- Anything anyone eats and isn’t killed by it, is food.
. Sue eats everything Bill eats.
(i) Translate the sentences into formulae in predicate logic. Prove that John likes peanuts using
backward chaining.
(ii) Convert the formulae of part (i) into clause form.
(ii) Prove that John likes peanuts using resolution.
8. What is the Turing test? If the machine passes the Turing test, does it mean that the system is intelligent? What are the associated problems with Turing test? What are required improvement/ advances to overcome these problems?
(b) What is the goal of the support vector machine (SVM)? How to compute the margin?