BSC CSIT Semester 4 – Artificial Intelligence () Questions & Answers | Past TU Exam Papers

Question 1

How 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.

Marks: 10

Year: 2081 Final TU

1. Relation Between Biological and Artificial Neural Networks | Biological Element | Role | Artificial Neural Network Equivalent | |-------------------|------|-------------------------------------| |

Question 2

What is reinforcement learning? Configure an ANN neuron to simulate OR gate.

Marks: 5

Year: 2081 Final TU

Reinforcement Learning & ANN OR Gate 1. What is Reinforcement Learning? Reinforcement Learning (RL) is a type of machine learning in which an agent learns by interacting with an environment. The ag

Question 3

What is reinforcement learning? Configure an ANN neuron to simulate OR gate.

Marks: 5

Year: 2081 Final TU

Reinforcement Learning & ANN OR Gate 1. What is Reinforcement Learning? Reinforcement Learning (RL) is a type of machine learning in which an agent learns by interacting with an environment. The ag

Question 4

Differentiate supervised learning from unsupervised? Discuss how Naïve Bayes Model can be used for machine learning ? Support your answer with example.

Marks: 10

Year: 2080 Final TU

Supervised vs Unsupervised Learning 1. Supervised Learning - Data comes with input–output pairs (labeled data). - The model learns a mapping from X → Y. - Used for classification (spam/ham) or regres

Question 5

Discuss how genetic algorithm works?

Marks: 5

Year: 2080 Final TU

How Genetic Algorithm (GA) Works A Genetic Algorithm (GA) is an optimization technique inspired by natural selection and evolution. It searches for the best solution by improving a population of can

Question 6

What is fuzzy logic? Discuss the different operators used in genetic algorithm

Marks: 5

Year: 2079 Final TU

What is Fuzzy Logic? Fuzzy Logic is a form of reasoning that deals with degrees of truth rather than strict true/false values. In classical logic, a statement is either 0 or 1, but in fuzzy logic it

Question 7

Give an example of reinforcement learning. Explain the types of ANN.

Marks: 5

Year: 2079 Final TU

Example of Reinforcement Learning (RL) Reinforcement Learning is a learning method where an agent learns by interacting with the environment and receiving rewards or penalties. Example: Robot Learnin

Question 8

Describe mathematical model of neural network. What does it means to train a neural network? Write algoritmn for preceptron learning.

Marks: 10

Year: 2078 Final TU

1. Mathematical Model of a Neural Network A neural network neuron performs three main operations: (a) Weighted Sum $$ net = \sum{i=1}^{n} wi xi + b $$ (b) Activation Function $$ y = f(net) $$ (c) F

Question 9

What is crossover operation in genetic algorithm? Given following chromosomes show the result of one-point and two point crossover. C1 = 01100010 C2 = 10101100 Choose appropriate crossover points as p

Marks: 5

Year: 2078 Final TU

Crossover Operation in Genetic Algorithm Crossover is a genetic operator used to combine the genetic information of two parents to generate new offspring. It simulates sexual reproduction in nature.

Question 10

What is prosterior probability? Consider a scenario that a patient have liver disease is 15% probability. A test says that 5% of patients are alcholic. Among those patients diagnosed with liver diseas

Marks: 5

Year: 2078 Final TU

Posterior Probability Posterior probability is the probability of an event occurring given some evidence. It is computed using Bayes’ Theorem: $$ P(A|B) = \frac{P(B|A) \cdot P(A)}{P(B)} $$ Where:

Question 11

Define mathematical model of artificial neural network. Discuss how Hebbian learning algorithm can be used to train a neural network. Support your answer with an example.

Marks: 10

Year: 2076 Final TU

1. Mathematical Model of Artificial Neural Network (ANN) An ANN is composed of neurons that process information using inputs, weights, bias, and an activation function. Neuron Model (a) Weighted Sum

Question 12

Write an algorithm for learning by Genetic Approach.

Marks: 5

Year: 2076 Final TU

Genetic Algorithm Learning (Genetic Approach) Genetic Algorithm (GA) is an optimization and learning technique inspired by natural evolution. It uses selection, crossover, and mutation to evolve bet

Question 13

Differentiate supervised learning from unsupervised learning. Discuss how Naïve Bayes Model can be used for machine learning. Support your answer with example.

Marks: 10

Year: 2080 Final TU

Supervised vs Unsupervised Learning and Naïve Bayes 1. Supervised Learning - Definition: Learning from a labeled dataset, where the input-output mapping is known. - Goal: Predict output (label) for

Question 14

Discuss how genetic algorithm works.

Marks: 5

Year: 2080 Final TU

Genetic Algorithm (GA) 1. Definition - GA is an optimization/search technique inspired by natural evolution. - Works by evolving a population of solutions using selection, crossover, and mutation.