This download link is referred from the post: AKTU B-Tech Last 10 Years 2010-2020 Previous Question Papers || Dr. A.P.J. Abdul Kalam Technical University
B.TECH. THEORY EXAMINATION (SEM–IV) 2016-17
INTRODUCTION TO SOFT COMPUTING (NEURAL NETWORK, FUZZY LOGIC & GENETIC ALGORITHM)
Time: 3 Hours
Max. Marks : 100
Note: Be precise in your answer.
--- Content provided by FirstRanker.com ---
SECTION – A
- Attempt the following: (10x2=20)
- Artificial Intelligence can be used in Neural Network or not. Justify your answer.
- Write different applications of neural networks.
- What is Reinforcement Learning?
- What do you mean by convergence of GA?
- What is the significance of fuzzy Quantifier?
- Define the fuzzy inference.
- What is the Mutation?
- Use the Hebb rule to store the vector [1 1 1 -1] in an auto-associative neural network
- What is FLC?
- Write the benefit of GA.
--- Content provided by FirstRanker.com ---
--- Content provided by FirstRanker.com ---
SECTION – B
- Attempt any 5 parts from the following 8 parts: (5x10=50)
- Define an artificial neural network. State the Characteristics of an artificial neural network.
- Discuss the factors affecting the training of back propagation neural network.
- Explain the different types of Operation used in Fuzzy Set with suitable examples
- Discuss the selection of Various parameter in BPN.
- What is Genetic Algorithm? Draw the general flow diagram of genetic algorithm.
- Differentiate between Roulette-wheel based on fitness and Roulette wheel based on ran with suitable example
- Find the weights required to perform the following classification using perceptron network. The vectors (1,1,1,1) and (-1,1-1,-1) are belonging to the class (so have target 1), vectors (1,1,1,-1) and (1,-1,-1,1) are not belonging to the class (so have target value -1). Assume learning rate is 1 and weights is 0.
- What are different attributes of predicate logic? Using inference in predicate logic prove following statement
- (i) All men are mortal
- (ii) Socrates is a man
--- Content provided by FirstRanker.com ---
--- Content provided by FirstRanker.com ---
SECTION - C
- Attempt any 2 parts from the following: (2x15=30)
- Explain the following Neural Network Architecture in Details:
- (i) Rosenblatt's Perceptron Model
- (ii) McCulloch- Pitts Model
- Explain the Greg Voit's Fuzzy Cruise Controller
- Use GA to solve the following non-linear programming problem: Minimize (x - 2.5)² + (y - 5)² subject to 5.5x + 2y² - 18 ≤ 0, 0≤x, y≥5.
--- Content provided by FirstRanker.com ---
- Explain the following Neural Network Architecture in Details:
--- Content provided by FirstRanker.com ---
This download link is referred from the post: AKTU B-Tech Last 10 Years 2010-2020 Previous Question Papers || Dr. A.P.J. Abdul Kalam Technical University