Generic selectors
Exact matches only
Search in title
Search in content
Search in posts
Search in pages
Filter by Categories
nmims post
Objective Type Set
Online MCQ Assignment
Question Solution
Solved Question
Uncategorized

Artificial Intelligence MCQ Set 1

1. Blind searching is general term for
a) Informed Search
b) Uninformed Search
c) Informed & Unformed Search
d) Heuristic Search

View Answer

Answer: b [Reason:] In case of uninformed search no additional information except the problem definition is given.

2. Strategies that know whether one non-goal state is “more promising” than another are called
a) Informed & Unformed Search
b) Unformed Search
c) Heuristic & Unformed Search
d) Informed & Heuristic Search

View Answer

Answer: d [Reason:] Strategies that know whether one non-goal state is “more promising” than another are called informed search or heuristic search strategies.

3. Which of the following is/are Uninformed Search technique/techniques
a) Breath First Search (BFS)
b) Depth First Search (DFS)
c) Bi-directional Search
d) All of the mentioned

View Answer

Answer: d [Reason:] Several uninformed search techniques includes BFS, DFS, Uniform-cost, Depth-limited, bi-directional search etc.

4. Which data structure conveniently used to implement BFS?
a) Stacks
b) Queues
c) Priority Queues
d) All of the mentioned

View Answer

Answer: b [Reason:] Queue is the most convenient data structure, but memory used to store nodes can be reduced by using circular queues.

5. Which data structure conveniently used to implement DFS?
a) Stacks
b) Queues
c) Priority Queues
d) All of the mentioned

View Answer

Answer: a [Reason:] DFS requires node to be expanded the one most recent visited, hence stack is convenient to implement.

6. The time and space complexity of BFS is (For time and space complexity problems consider b as branching factor and d as depth of the search tree.)
a) O(bd+1) and O(bd+1)
b) O(b2) and O(d2)
c) O(d2) and O(b2)
d) O(d2) and O(d2)

View Answer

Answer: a [Reason:] We consider a hypothetical state space where every state has b successors. The root of the search tree generates b nodes at the first level, each of which generates b more nodes, for a total of b2 at the second level. Each of these generates b more nodes, yielding b3 nodes at the third level, and so on. Now suppose that the solution is at depth d. In the worst case, we would expand all but the last node at level d (since the goal itself is not expanded), generating bd+1- b nodes at level d+1.

7. Breadth-first search is not optimal when all step costs are equal, because it always expands the shallowest unexpanded node. State whether true or false.
a) True
b) False

View Answer

Answer: b [Reason:] Breadth-first search is optimal when all step costs are equal, because it always expands the shallowest unexpanded node. If the solution exists in shallowest node no irrelevant nodes are expanded.

8. uniform-cost search expands the node n with the__________
a) Lowest path cost
b) Heuristic cost
c) Highest path cost
d) Average path cost

View Answer

Answer: a [Reason:] Uniform-cost search expands the node n with the lowest path cost. Note that if all step costs are equal, this is identical to breadth-first search.

9. Depth-first search always expands the ______ node in the current fringe of the search tree.
a) Shallowest
b) Child node
c) Deepest
d) Minimum cost

View Answer

Answer: c [Reason:] Depth-first search always expands the deepest/leaf node in the current fringe of the search tree.

10. Breadth-first search always expands the ______ node in the current fringe of the search tree.
a) Shallowest
b) Child node
c) Deepest
d) Minimum cost

View Answer

Answer: a [Reason:] Breadth-first search always expands the shallowest node in the current fringe of the search tree. Traversal is performed level wise.

11. Optimality of BFS is
a) When there is less number of nodes
b) When all step costs are equal
c) When all step costs are unequal
d) None of the mentioned

View Answer

Answer: b [Reason:] It always expands the shallowest unexpanded node.

12. LIFO is ______ where as FIFO is ________
a) Stack, Queue
b) Queue, Stack
c) Priority Queue, Stack
d) Stack. Priority Queue

View Answer

Answer: a [Reason:] LIFO is last in first out – Stack. FIFO is first in first out – Queue.

13. When the environment of an agent is partially observable in search space following problem/problems could occur.
a) Sensorless problems: If the agent has no sensors at all, then (as far as it knows) it could be in one of several possible initial states, and each action might therefore lead to one of several possible successor states
b) Contingency problems: If the environment is partially observable or if actions are uncertain, then the agent’s percepts provide new information after each action. Each possible percept defines a contingency that must be planned for. A problem is called adversarial if the uncertainty is caused by the actions of another agent
c) Exploration problems: When the states and actions of the environment are unknown, the agent must act to discover them. Exploration problems can be viewed as an extreme case of contingency problems
d) All of the mentioned

View Answer

Answer: d [Reason:] None.

14. For general graph, how one can get rid of repeated states?
a) By maintaining a list of visited vertices
b) By maintaining a list of traversed edges
c) By maintaining a list of non-visited vertices
d) By maintaining a list of non-traversed edges

View Answer

Answer: a [Reason:] Other techniques are costly.

15. DFS is ______ efficient and BFS is __________ efficient.
a) Space, Time
b) Time, Space
c) Time, Time
d) Space, Space

View Answer

Answer: a [Reason:] http://mhesham.wordpress.com/tag/bfs-vs-dfs/

16. The main idea of bi-directional search is to reduce the time complexity by searching two way simultaneously from start node and another from goal node.
a) True
b) False

View Answer

Answer: a [Reason:] The idea behind bidirectional search is to run two simultaneous searches-one forward from the initial state and the other backward from the goal, stopping when the two searches meet in the middle. The motivation is that bd/2 + bd/2 is much less than bd.

Artificial Intelligence MCQ Set 2

1. Which search strategy is also called as blind search?
a) Uninformed search
b) Informed search
c) Simple reflex search
d) All of the mentioned

View Answer

Answer: a [Reason:] In blind search, We can search the states without having any additional information. So uninformed search method is blind search.

2. How many types are available in uninformed search method?
a) 3
b) 4
c) 5
d) 6

View Answer

Answer: c [Reason:] The five types of uninformed search method are Breadth-first, Uniform-cost, Depth-first, Depth-limited and Bidirectional search.

3. Which search is implemented with an empty first-in-first-out queue?
a) Depth-first search
b) Breadth-first search
c) Bidirectional search
d) None of the mentioned

View Answer

Answer: b [Reason:] Because of FIFO queue, it will assure that the nodes that are visited first will be expanaded first.

4. When is breadth-first search is optimal?
a) When there is less number of nodes
b) When all step costs are equal
c) When all step costs are unequal
d) None of the mentioned

View Answer

Answer: b [Reason:] Because it always expands the shallowest unexpanded node.

5. How many successors are generated in backtracking search?
a) 1
b) 2
c) 3
d) 4

View Answer

Answer: a [Reason:] Each partially expanded node remembers which successor to generate next because of these condition, it uses less memory.

6. What is the space complexity of Depth-first search?
a) O(b)
b) O(bl)
c) O(m)
d) O(bm)

View Answer

Answer: d [Reason:] O(bm) is the space complexity where b is the branching factor andm is the maximum depth of the search tree.

7. How many parts does a problem consists of?
a) 1
b) 2
c) 3
d) 4

View Answer

Answer: d [Reason:] The four parts of the problem are intial state, set of actions, goal test and path cost.

8. Which algorithm is used to solve any kind of problem?
a) Breath-first algorithm
b) Tree algorithm
c) Bidirectional search algorithm
d) None of the mentioned

View Answer

Answer: b [Reason:] Tree algorithm is used because specific variants of the algorithm embed different strategies.

9. Which search algorithm imposes a fixed depth limit on nodes?
a) Depth-limited search
b) Depth-first search
c) Iterative deepening search
d) Bidirectional search

View Answer

Answer: a [Reason:] None.

10. Which search implements stack operation for searching the states?
a) Depth-limited search
b) Depth-first search
c) Breadth-first search
d) None of the mentioned

View Answer

Answer: b [Reason:] It implements stack operation because it always expands the deepest node in the current tree.

Artificial Intelligence MCQ Set 3

1. LISP machines also are known as:
a) AI workstations
b) Time-sharing terminals
c) Super mini computers
d) All of the mentioned

View Answer

Answer: a [Reason:] None.

2. Natural language processing can be divided into the two sub-fields of:
a) context and expectations
b) generation and understanding
c) semantics of pragmatics
d) recognition and synthesis

View Answer

Answer: b [Reason:] None.

3. How many ALU(s) is/are control by one control unit is SIMD (single instruction stream, multiple data stream) architecture?
a) one or more ALUs
b) One ALU
c) Only two ALU
d) Impossible to say

View Answer

Answer: a [Reason:] None.

4. Which of the following function returns t if the object is a number in LISP?
a) (number <object>)
b) (numberp <object>)
c) (numericp <object>)
d) (numeric <object>)

View Answer

Answer: b [Reason:] None.

5. Which of the following have computers traditionally done better than people?
a) storing information
b) responding flexibly
c) computing numerically
d) both storing information & computing numerically

View Answer

Answer: d [Reason:] None.

6. The characteristics of the computer system capable of thinking, reasoning and learning is known is
a) machine intelligence
b) human intelligence
c) artificial intelligence
d) virtual intelligence

View Answer

Answer: c [Reason:] None.

7. What part of the manufacturing process relate to each stage of the process and to the process as a whole?
a) field service
b) design
c) distribution
d) project management

View Answer

Answer: d [Reason:] None.

8. The area of AI that investigates methods of facilitating communication between people and computers is:
a) natural language processing
b) symbolic processing
c) decision support
d) robotics

View Answer

Answer: a [Reason:] None.

9. In the 16th century, a Czech rabbi reportedly created a living clay man whose name has become a synonym for an artificial human. The clay man’s name was:
a) Frankenstein
b) Golem
c) Paracelsus
d) Hal

View Answer

Answer: b [Reason:] None.

10. For speech understanding systems to gain widespread acceptance in office automation, they must feature:
a) speaker independence
b) speaker dependence
c) isolated word recognition
d) all of the mentioned

View Answer

Answer: a [Reason:] None.

Artificial Intelligence MCQ Set 4

1. The conference that launched the AI revolution in 1956 was held at:
a) Dartmouth
b) Harvard
c) New York
d) Stanford

View Answer

Answer: a [Reason:] None.

2. Texas Instruments Incorporated produces a low-cost LISP machine called:
a) The Computer-Based Consultant
b) The Explorer
c) Smalltalk
d) The Personal Consultant

View Answer

Answer: b [Reason:] None.

3. When a top-level function is entered, the LISP processor do(es)
a) It reads the function entered
b) It evaluates the function and the function’s operands
c) It prints the results returned by the function
d) All of the mentioned

View Answer

Answer: d [Reason:] None.

4. One method of programming a computer to exhibit human intelligence is called modeling or:
a) simulation
b) cognitization
c) duplication
d) psychic amelioration

View Answer

Answer: a [Reason:] None.

5. Graphic interfaces were first used in a Xerox product called:
a) InterLISP
b) Ethernet
c) Smalltalk
d) ZetaLISP

View Answer

Answer: c [Reason:] None.

6. The Al researcher who co-authored both the Handbook of Artificial Intelligence and The Fifth Generation is:
a) Bruce Lee
b) Randy Davis
c) Ed Feigenbaum
d) Mark Fox

View Answer

Answer: c [Reason:] None.

7. Which of the following is being investigated as a means of automating the creation of a knowledge base?
a) automatic knowledge acquisition
b) simpler tools
c) discovery of new concepts
d) all of the mentioned

View Answer

Answer: d [Reason:] None.

8. The CAI (Computer-Assisted Instruction) technique based on programmed instruction is:
a) frame-based CAI
b) generative CAI
c) problem-solving CAI
d) intelligent CAI

View Answer

Answer: a [Reason:] None.

9. A robot’s “arm” is also known as its:
a) end effector
b) actuator
c) manipulator
d) servomechanism

View Answer

Answer: c [Reason:] None.

10. KEE is a product of:
a) Teknowledge
b) IntelliCorpn
c) Texas Instruments
d) Tech knowledge

View Answer

Answer: b [Reason:] None.

11. In LISP, the function X (x). (2x+l) would be rendered as
a) (lambda (x) (+(*2 x)l))
b) (lambda (x) (+1 (* 2x)
c) (+ lambda (x) 1 (*2x))
d) (* lambda(x) (+2×1)

View Answer

Answer: a [Reason:] None.

12. A natural language generation program must decide:
a) what to say
b) when to say something
c) why it is being used
d) both what to say & when to say something

View Answer

Answer: a [Reason:] None.

13. The hardware features of LISP machines generally include:
a) large memory and a high-speed processor
b) letter-quality printers and 8-inch disk drives
c) a mouse and a specialized keyboard
d) large memory and a high-speed processor & a mouse and a specialized keyboard

View Answer

Answer: d [Reason:] None.

14. In which of the following areas may ICAI programs prove to be useful?
a) educational institutions
b) corporations
c) department of Defense
d) all of the mentioned

View Answer

Answer: a [Reason:] None.

5. A network with named nodes and labeled arcs that can be used to represent certain natural language grammars to facilitate parsing.
a) Tree Network
b) Star Network
c) Transition Network
d) Complete Network

View Answer

Answer: c [Reason:] None.

Artificial Intelligence MCQ Set 5

1. Why is the XOR problem exceptionally interesting to neural network researchers?
a) Because it can be expressed in a way that allows you to use a neural network
b) Because it is complex binary operation that cannot be solved using neural networks
c) Because it can be solved by a single layer perceptron
d) Because it is the simplest linearly inseparable problem that exists.

View Answer

Answer: d [Reason:] None.

2. What is back propagation?
a) It is another name given to the curvy function in the perceptron
b) It is the transmission of error back through the network to adjust the inputs
c) It is the transmission of error back through the network to allow weights to be adjusted so that the network can learn
d) None of the mentioned

View Answer

Answer: c [Reason:] Back propagation is the transmission of error back through the network to allow weights to be adjusted so that the network can learn.

3. Why are linearly separable problems of interest of neural network researchers?
a) Because they are the only class of problem that network can solve successfully
b) Because they are the only class of problem that Perceptron can solve successfully
c) Because they are the only mathematical functions that are continue
d) Because they are the only mathematical functions you can draw

View Answer

Answer: b [Reason:] Linearly separable problems of interest of neural network researchers because they are the only class of problem that Perceptron can solve successfully.

4. Which of the following is not the promise of artificial neural network?
a) It can explain result
b) It can survive the failure of some nodes
c) It has inherent parallelism
d) It can handle noise

View Answer

Answer: a [Reason:] The artificial Neural Network (ANN) cannot explain result.

5. Neural Networks are complex ______________ with many parameters.
a) Linear Functions
b) Nonlinear Functions
c) Discrete Functions
d) Exponential Functions

View Answer

Answer: a [Reason:] Neural networks are complex linear functions with many parameters.

6. A perceptron adds up all the weighted inputs it receives, and if it exceeds a certain value, it outputs a 1, otherwise it just outputs a 0.
a) True
b) False
c) Sometimes – it can also output intermediate values as well
d) Can’t say

View Answer

Answer: a [Reason:] Yes the perceptron works like that.

7. The name for the function in question 16 is
a) Step function
b) Heaviside function
c) Logistic function
d) Perceptron function

View Answer

Answer: b [Reason:] Also known as the step function – so answer 1 is also right. It is a hard thresholding function, either on or off with no in-between.

8. Having multiple perceptrons can actually solve the XOR problem satisfactorily: this is because each perceptron can partition off a linear part of the space itself, and they can then combine their results
a) True – this works always, and these multiple perceptrons learn to classify even complex problems
b) False – perceptrons are mathematically incapable of solving linearly inseparable functions, no matter what you do
c) True – perceptrons can do this but are unable to learn to do it – they have to be explicitly hand-coded
d) False – just having a single perceptron is enough

View Answer

Answer: c [Reason:] None.

9. The network that involves backward links from output to the input and hidden layers is called as ____
a) Self organizing maps
b) Perceptrons
c) Recurrent neural network
d) Multi layered perceptron

View Answer

Answer: c [Reason:] RNN (Recurrent neural network) topology involves backward links from output to the input and hidden layers.

10. Which of the following is an application of NN (Neural Network)?
a) Sales forecasting
b) Data validation
c) Risk management
d) All of the mentioned

View Answer

Answer: d [Reason:] All mentioned options are applications of Neural Network.