Units_1_and_2_MCQ PDF

Preview

Summary

Units_1_and_2_MCQ...

Description

UNIT 1 and UNIT 2 Soft Computing Techniques Question Bank (MCQ and Subjetive Type ) 1. Neural Computing A. mimics human brain B. information processing paradigm C. Both (a) and (b) D. None of the above Option: C 2. What are the 2 types of learning A. Improvised and unimprovised B. supervised and unsupervised C. Layered and unlayered D. None of the above Option: B 3. Supervised Learning is A. learning with the help of examples B. learning without teacher C. learning with the help of teacher D. learning with computers as supervisor 4. Unsupervised learning is A. learning without computers B. problem based learning C. learning from environment D. learning from teachers 5. Conventional Artificial Intelligence is different from soft computing in the sense A. Conventional Artificial Intelligence deal with prdicate logic where as soft computing deal with fuzzy logic

B. Conventional Artificial Intelligence methods are limited by symbols where as soft computing is based on empirical data C. Both (a) and (b) D. None of the above 6. Which search strategy is also called as blind search? a. Uninformed search b. Informed search c. Simple reflex search d. All of the mentioned 7. What is the other name of informed search strategy? a. Simple search b. Heuristic search c. Online search d. None of the mentioned

8. Which search uses the problem specific knowledge beyond the definition of the problem? a. Informed search b. Depth-first search c. Breadth-first search d. Uninformed search 9. Which solution would DFS find to move from node S to node G if run on the graph below?

10)

Which is not commonly used programming language for AI?

Perl language is not commonly used programming language for AI 11)

What is Prolog in AI?

In AI, Prolog is a programming language based on logic. 12)

Give an explanation on the difference between strong AI and weak AI?

Strong AI makes strong claims that computers can be made to think on a level equal to humans

while weak AI simply predicts that some features that are resembling to human intelligence can be incorporated to computer to make it more useful tools. 13)

Mention the difference between statistical AI and Classical AI ?

Statistical AI is more concerned with “inductive” thought like given a set of pattern, induce the trend etc. While, classical AI, on the other hand, is more concerned with “ deductive” thought given as a set of constraints, deduce a conclusion etc. 14)

Which search method takes less memory?

The “depth first search” method takes less memory. 15)

Which is the best way to go for Game playing problem?

Heuristic approach is the best way to go for game playing problem, as it will use the technique based on intelligent guesswork. For example, Chess between humans and computers as it will use brute force computation, looking at hundreds of thousands of positions. 16) What is Artificial Intelligence? Artificial Intelligence is an area of computer science that emphasizes the creation of intelligent machine that work and reacts like humans. 17) What are the various areas where AI (Artificial Intelligence) can be used? Artificial Intelligence can be used in many areas like Computing, Speech recognition, Bioinformatics, Humanoid robot, Computer software, Space and Aeronautics’s etc. 18) What is a heuristic function? A heuristic function ranks alternatives, in search algorithms, at each branching step based on the available information to decide which branch to follow. 19) Mention the difference between breadth first search and best first search in artificial intelligence? These are the two strategies which are quite similar. In best first search, we expand the nodes in accordance with the evaluation function. While, in breadth first search a node is expanded in accordance to the cost function of the parent node. 20) What is FOPL stands for and explain its role in Artificial Intelligence? FOPL stands for First Order Predicate Logic, Predicate Logic provides a)

A language to express assertions about certain “World”

b) An inference system to deductive apparatus whereby we may draw conclusions from such assertion c)

A semantic based on set theory

21. ANN is composed of large number of highly interconnected processing elements(neurons) working in unison to solve problems. A. True B. False 7. Artificial neural network used for A. Pattern Recognition B. Classification C. Clustering D. All of these

22. Ability to learn how to do tasks based on the data given for training or initial experience A. Self Organization B. Adaptive Learning C. Fault tolerance D. Robustness

23. In artificial Neural Network interconnected processing elements are called A. nodes or neurons B. weights C. axons D. Soma 24. Each connection link in ANN is associated with ________ which has information about the input signal. A. neurons B. weights C. bias D. activation function 25. What is Artificial intelligence? (a) Putting your intelligence into Computer (b) Programming with your own intelligence

(c) Making a Machine intelligent (d) Playing a Game (e) Putting more memory into Computer 26. Which is not the commonly used programming language for AI? (a) PROLOG (b) Java (c) LISP (d) Perl

(e) Java script.

27. What is state space? (a) The whole problem (b) Your Definition to a problem (c) Problem you design (d) Representing your problem with variable and parameter (e) A space where You know the solution. 28. A production rule consists of (a) A set of Rule (c) Both (a) and (b) (e) Directly getting solution.

(b) A sequence of steps (d) Arbitrary representation to problem

29. Which search method takes less memory? (a) Depth-First Search (b) Breadth-First search (c) Both (a) and (b) (d) Linear Search. (e) Optimal search. 30. A heuristic is a way of trying (a) To discover something or an idea embedded in a program (b) To search and measure how far a node in a search tree seems to be from a goal (c) To compare two nodes in a search tree to see if one is better than the other (d) Only (a) and (b) (e) Only (a), (b) and (c). 31. Which is the best way to go for Game playing problem? (a) Linear approach (b) Heuristic approach (c) Random approach (d) Optimal approach (e) Stratified approach. 32. How do you represent “All dogs have tails”. (a) ۷ x: dog(x)àhastail(x) (b) ۷ x: dog(x)àhastail(y) (c) ۷ x: dog(y)àhastail(x) (d) ۷ x: dog(x)àhasàtail(x) (e) ۷ x: dog(x)àhasàtail(y) 33. What are you predicating by the logic: ۷ x: €y: loyalto(x, y). (a) Everyone is loyal to some one (b) Everyone is loyal to all (c) Everyone is not loyal to someone (d) Everyone is loyal (e) Everyone is not loyal.

1. There are two water jugs of 5 L and 3 L, Write the sequences for filling a) 2 L in 3L Jug, b) 1L in 3 L Jug c) 2L in 5L Jug d) 3L in 5L Jug e) 1L in 5L Jug f) 4L in 5L Jug if there are no markings on the jugs. Let the starting sequence is (0,0), where both the jugs are empty. 2. There are two water jugs of 4 L and 3 L, Write the sequences for filling a) 2 L in 3L Jug, b) 1L in 3 L Jug c) 2L in 4L Jug d) 3L in 4L Jug e) 1L in 4 L Jug if there are no markings on the jugs. Let the starting sequence is (0,0), where both the jugs are empty. 3. Find the goal state using a) Breadth First Search, b) Deapth First Search and c) Best First Search for the following search tree. The heuristic function values are given in each node and the goal state is to be considered as maximum value of heuristic function. Write the path.

4. Repeat the above problem, if the goal state is to be considered as minimum value of heuristic function. Write the path. 5. Explain both Depth first search and Breadth first search method to find out the goal state for a given search tree, a) if heuristic function is the minimum value and b) if heuristic funcion is the maximum value.

6. Use Problem reduction technique to to choose the best method of matrix multiplication for the 3 matrices given A: 3 * 4; B: 4*10; C:10*1; using cost function and dimention.

7. Use Hill climbing method to reach the goal state 7 and also specify the path. The initial state is 8. The values mentioned in the node indicates the state number.

8. Explain the Generate and Test Algorithm steps along with a suitable block diagram. 9. Use Best First search algorithm to search for a goal state having less heuristic function value. The values in the search tree for each node indicates heuristic function.

10. Write the sequences for Man,Goat,Lion and cabbage problem to cross the river from one side to other side. 11. Define Plateu, Local maxima and Ridge problem in Simple hill climbing technique. 12. Draw with neat diagrams showing the analogy between Biological neural network and Artificial neural network with brief explanation. 13. Explain about Learning techniques and also draw the taxonomy of popular learning techniques of neural network. 14. Derive the expression for new or updated synaptic weight for a neural network using Gradient Decent Technique. 15. List the mathematical equations in deriving derivative of Error function with synaptic weight in Back propagation algorithm and explain each terms. 16. Represent the Neural network for 2input AND gate using atleast two different cases of weights and mention the threshold values. 17. List four different types of acivation functions used in neural network with suitable graph and corresponding equations. 18. For a neural network inputs x1 = 0.15, x2 = 0.2, bias b1 = 0.45. Find net (Y1), out (Y1), net (Y2) and out(Y2), if sigmoid function is used as activation function. Note Y1 and Y2 are the output neurons. Bias b1 is connected to both outputs Y1 and Y2. W1 = 0.25 and W2 = 0.3 are the weights connected from x1 to Y1 and x2 to Y1 respectively. Similarly, W3 = 0.35 and W4 = 0.4 are the weights connected from x1 to Y2 and x2 to Y2 respectively. 19. For the above problem targets T1 = 0.01 and Target T2 = 0.99, Calculate the Total error and individual errors of neurons. 20. For a back propagation neural network, inputs x1 = 0.25, x2 = 0.3 and bias b1 = 0.45.

Find net (Y1), out (Y1), net(Y2) and out(Y2), if sigmoid function is used as activation function. Note Y1 and Y2 are the output neurons. Bias b1 is connected to both outputs Y1 and Y2. W1 = 0.35 and W2 = 0.4 are the weights connected from x1 to Y1 and x2 to Y1 respectively. Similarly, W3 = 0.5 and W4 = 0.55 are the weights connected from x1 to Y2 and x2 to Y2 respectively. Calculate the individual errors of Y1 and Y2. Find the total Error, if Targets are T1 = 0.01 and T2 = 0.99. 21. Give the taxonomy of different learning techniques in neural network. 22. For a feed forward neural network with one hidden layer and 2 inputs (x1 and x2) and 2 outputs (Y1 and Y2), calculate the total error: The following details are given: Inputs : x1 = 0.05, x2 = 0.10 ; Weights from first layer to input layer: w1=0.15 (x1->H1); w2=0.2(x2->H1); w3 = 0.25 (x1->H2) ; w4 = 0.3 (x2-> H2); Bias b1 =0.35 (applied to both H1 and H2). Weights from hidden layer to output layer: w5=0.4(H1->Y1); w6=0.45 (H2->Y1); w7 = 0.5 (H1->Y2) ; w8= 0.55 (H2->Y2); Bias b2 =0.6 (applied to both Y1 and Y2) The target values are T1 = 0.01 and T2 = 0.99; Use Sigmoid activation function. 23. For a Backpropagation neural network with one hidden layer and 2 inputs (x1 and x2) and 2 outputs(Y1 and Y2), calculate the total error and also find the updated synaptic weights: Check that error after the first iteration will be rduced. The following details are given: Inputs : x1 = 0.05, x2 = 0.10, ; Weights from first layer to input layer: w1=0.15 (x1->H1); w2=0.2(x2->H1); w3 = 0.25 (x1->H2) ; w4 = 0.3 (x2-> H2); Bias b1 =0.35 (applied to both H1 and H2). Weights from hidden layer to output layer: w5=0.4(H1->Y1); w6=0.45 (H2->Y1); w7 = 0.5 (H1->Y2) ; w8= 0.55 (H2->Y2); Bias b2 =0.6 (applied to both Y1 and Y2) The target values are T1 = 0.01 and T2 = 0.99; Use Sigmoid activation function. 24. Construct and test a BAM network to associate letters A and B with suitable Bipolar inputoutput vectors. Target output for A is (-1,1) and for B is (1,1). Display Matrix Size is 5*3. 25 Use Problem reduction technique to to choose the best method of matrix multiplication for the 3 matrices given A: 3 * 5; B: 5*9; C:9*1; using cost function and dimention. 26. Explain Means Ends Analysis with a step by step procedure along with a standard example to justify the same. 27. Derive the expression for new or updated synaptic weight for a neural network using Gradient Decent Technique. 28. List the mathematical equations in deriving derivative of Error function with synaptic weight in Back propagation algorithm and explain each terms. 29. Explain Steepest Descent hill climbing algorithm. 30. Explain about Search tree and state space....