TRIBHUVAN UNIVERSITY
INSTITUTE OF SCIENCE AND TECHNOLOGY
2081 B.S.
Candidates are required to give their answers in their own words as far as practicable.
Group A
Long Answer QuestionsAttempt any Two questions.
- 1How can you relate synapse, dendrite, and axon in biological neural networks with the elements of artificial neural networks? Create a multi-layer ANN with input layer, hidden layer and output layer. Assume necessary inputs and weights to the ANN and illustrate a single iteration of back propagation algorithm to train the ANN.
- 2What is Skolem constant? How is Skolemization done during resolution? Represent the following statements into FOPL. All movies are not hit. Sarangi is a movie. All movies which has good script are hit Sarangi has a good script but Sarangi is sentimental. There is a movie which is comedy.
- 3How is informed search different from uninformed search? Create a state space with appropriate heuristics, now illustrate how hill climbing search expands nodes to reach a goal. Modify the state space heuristics and demonstrate when the hill climbing will not be complete.
Group B
Short Answer QuestionsAttempt any Eight questions.
- 4What is intelligence? Describe the foundations of AI.
- 5What is a rational agent? Justify with example how goal-based agent works?
- 6How uniform cost search is used to search goal in the state space? Illustrate with example.
- 7How can you represent knowledge using scripts? Create a knowledge base using script based on your own assumption.
- 8What is reinforcement learning? Configure an ANN neuron to simulate OR gate.
- 9What is robotics? How machine vision is used in robotics?
- 10Define fuzzy logic? Construct a fuzzy rule base expert system with your own considerations of fuzzy sets.
- 11How is the minimax algorithm used in game search? Consider state space is defined by a collection of pairs like $(A, B)$ representing paths between states $A$ and $B$. Construct state space for following and use a minimax algorithm. $(A, B), (A, C), (B, D), (D, E), (C, F), (C, G), (D, H), (D, I), (E, J), (F, K), (F, L), (G, M), (G, N)$. The utilities for states $H, I, J, K, L, M, N$ are $1, 3, 2, 6, 3, 4, 1$ respectively.
- 12Justify which types of environments resembles following agents. a. Mission Game with fixed $6$ states having two players b. Tesla Driverless Robovan where road conditions are changing c. Game Result Predicting Agent where current prediction state is independent of previous state.