Artificial Intelligence MCQ Set 1
1. A 3-input neuron is trained to output a zero when the input is 110 and a one when the input is 111. After generalization, the output will be zero when and only when the input is:
a) 000 or 110 or 011 or 101
b) 010 or 100 or 110 or 101
c) 000 or 010 or 110 or 100
d) 100 or 111 or 101 or 001
Answer
Answer: c [Reason:] The truth table before generalization is:
Inputs Output
000 $
001 $
010 $
011 $
100 $
101 $
110 0
111 1
where $ represents don’t know cases and the output is random.
After generalization, the truth table becomes:
Inputs Output
000 0
001 1
010 0
011 1
100 0
101 1
110 0
111 1
.
2. A perceptron is:
a) a single layer feed-forward neural network with pre-processing
b) an auto-associative neural network
c) a double layer auto-associative neural network
d) a neural network that contains feedback
Answer
Answer: a [Reason:] The perceptron is a single layer feed-forward neural network. It is not an auto-associative network because it has no feedback and is not a multiple layer neural network because the pre-processing stage is not made of neurons.
3. An auto-associative network is:
a) a neural network that contains no loops
b) a neural network that contains feedback
c) a neural network that has only one loop
d) a single layer feed-forward neural network with pre-processing
Answer
Answer: b [Reason:] An auto-associative network is equivalent to a neural network that contains feedback. The number of feedback paths(loops) does not have to be one.
4. A 4-input neuron has weights 1, 2, 3 and 4. The transfer function is linear with the constant of proportionality being equal to 2. The inputs are 4, 10, 5 and 20 respectively. The output will be:
a) 238
b) 76
c) 119
d) 123
Answer
Answer: a [Reason:] The output is found by multiplying the weights with their respective inputs, summing the results and multiplying with the transfer function. Therefore:
Output = 2 * (1*4 + 2*10 + 3*5 + 4*20) = 238.
5. Which of the following is true?
(i) On average, neural networks have higher computational rates than conventional computers.
(ii) Neural networks learn by example.
(iii) Neural networks mimic the way the human brain works.
a) All of the mentioned are true
b) (ii) and (iii) are true
c) (i), (ii) and (iii) are true
d) None of the mentioned
Answer
Answer: a [Reason:] Neural networks have higher computational rates than conventional computers because a lot of the operation is done in parallel. That is not the case when the neural network is simulated on a computer. The idea behind neural nets is based on the way the human brain works. Neural nets cannot be programmed, they cam only learn by examples.
6. Which of the following is true for neural networks?
(i) The training time depends on the size of the network.
(ii) Neural networks can be simulated on a conventional computer.
(iii) Artificial neurons are identical in operation to biological ones.
a) All of the mentioned
b) (ii) is true
c) (i) and (ii) are true
d) None of the mentioned
Answer
Answer: c [Reason:] The training time depends on the size of the network; the number of neuron is greater and therefore the number of possible ‘states’ is increased. Neural networks can be simulated on a conventional computer but the main advantage of neural networks – parallel execution – is lost. Artificial neurons are not identical in operation to the biological ones.
7. What are the advantages of neural networks over conventional computers?
(i) They have the ability to learn by example
(ii) They are more fault tolerant
(iii)They are more suited for real time operation due to their high ‘computational’ rates
a) (i) and (ii) are true
b) (i) and (iii) are true
c) Only (i)
d) All of the mentioned
Answer
Answer: d [Reason:] Neural networks learn by example. They are more fault tolerant because they are always able to respond and small changes in input do not normally cause a change in output. Because of their parallel architecture, high computational rates are achieved.
8. Which of the following is true?
Single layer associative neural networks do not have the ability to:
(i) perform pattern recognition
(ii) find the parity of a picture
(iii)determine whether two or more shapes in a picture are connected or not
a) (ii) and (iii) are true
b) (ii) is true
c) All of the mentioned
d) None of the mentioned
Answer
Answer: a [Reason:] Pattern recognition is what single layer neural networks are best at but they don’t have the ability to find the parity of a picture or to determine whether two shapes are connected or not.
9. Which is true for neural networks?
a) It has set of nodes and connections
b) Each node computes it’s weighted input
c) Node could be in excited state or non-excited state
d) All of the mentioned
Answer
Answer: d [Reason:] All mentioned are the characteristics of neural network.
10. Neuro software is:
a) A software used to analyze neurons
b) It is powerful and easy neural network
c) Designed to aid experts in real world
d) It is software used by Neuro surgeon
Answer
Answer: b [Reason:] None.
Artificial Intelligence MCQ Set 2
1. What enables people to recognize people, animals and inanimate objects reliably?
a) Speech
b) Vision
c) Hear
d) Perception
Answer
Answer: b [Reason:] Vision enables people to recognize people, animals and inanimate objects reliably. It is customary to use object recognition.
2. How many types of recognition are there in artificial intelligence?
a) 1
b) 2
c) 3
d) 4
Answer
Answer: c [Reason:] The three types of recognition are biometric identification, content-based image retrievel and handwriting recognition.
3. Which are recognized by vision?
a) Objects
b) Activities
c) Motion
d) Both Objects & Activities
Answer
Answer: d [Reason:] Vision is used to recognize not only objects, but also activities.
4. Which provides a framework for studying object recognition?
a) Learning
b) Unsupervised learning
c) Supervised learning
d) None of the mentioned
Answer
Answer: c [Reason:] Supervised learning or pattern classification provides a framework for studying object recognition.
5. Which object recognition process is an error-prone process?
a) Bottom-up segmentation
b) Top-down segmentation
c) Both Bottom-up & Top-down segmentation
d) None of the mentioned
Answer
Answer: a [Reason:] In the process of creating subset of pixels, the bottom-up segmentation is an error-prone process.
6. Which is the only way to learn about the different kinds of human faces?
a) Perception
b) Speech
c) Learning
d) Hearing
Answer
Answer: c [Reason:] None.
7. What can be represented by using histograms or empirical frequency distributions?
a) Words
b) Color
c) Texture
d) Both Color & Texture
Answer
Answer: d [Reason:] Color and texture can be represented by using histograms or empirical frequency distributions.
8. Which can be deformed into alignment using simple coordinate transformations?
a) Matching
b) Deformable matching
c) Feature
d) All of the mentioned
Answer
Answer: b [Reason:] The distance between images can be deformed into alignment using simple coordinate transformations. And it is called as Deformable matching.
9. Which describes the coarse arrangement of the rest of the shape with respect to the point?
a) Shape
b) Context
c) Shape context
d) None of the mentioned
Answer
Answer: c [Reason:] Because an objects shape can be manipulated with respect to the point.
10. How the distance between two shapes can be definied?
a) Weighted sum of the shape
b) Size of the shape
c) Shape context
d) None of the mentioned
Answer
Answer: a [Reason:] The distance between two shapes can be definied as a weighted sum of the shape context distance between corresponding points.
Artificial Intelligence MCQ Set 3
1. Which search agent operates by interleaving computation and action?
a) Offline search
b) Online search
c) Breadth-first search
d) Depth-first search
Answer
Answer: b [Reason:] In online search, it will first take an action and then observes the environment.
2. What is called as exploration problem?
a) State and actions are unknown to the agent
b) State and actions are known to the agent
c) Only actions are known to agent
d) None of the mentioned
Answer
Answer: a [Reason:] Online search is a necessary idea for an exploration problem where the states and actions are unknown to the agent.
3. Which are necessary for an agent to solve an online search problem?
a) Actions
b) Step-cost function
c) Goal-test
d) All of the mentioned
Answer
Answer: d [Reason:] An online search problem can be solved by an agent executing actions, So these functions are necessary.
4. When do we call the states are safely explorable?
a) A goal state is unreachable from any state
b) A goal state is denied access
c) A goal state is reachable from every state
d) None of the mentioned
Answer
Answer: c [Reason:] None
5. In which state spaces does the online-dfs-agent will work?
a) Irreversible state spaces
b) Reversible state spaces
c) searchable state spaces
d) All of the mentioned
Answer
Answer: b [Reason:] Online-DFS-Agent will work only state spaces where the actions are reversible.
6. Which of the following algorithm is online search algorithm?
a) Breadth-first search algorithm
b) Depth-first search algorithm
c) Hill-climbing search algorithm
d) None of the mentioned
Answer
Answer: c [Reason:] Hill-climbing search algorithm will have only current state in memory, So it is a online search algorithm.
7. Which search algorithm will use limited amount of memory?
a) RBFS
b) SMA*
c) Hill-climbing search algorithm
d) Both RBFS & SMA*
Answer
Answer: d [Reason:] RBFE and SMA* will solve any kind of problem that A* can’t by using limited amount of memory.
8. What is meant by simulated annealing in artifical intelligence?
a) Returns an optimal solution when there is a proper cooling schedule
b) Returns an optimal solution when there is no proper cooling schedule
c) It will not return an optimal solution when there is a proper cooling schedule
d) None of the mentioned
Answer
Answer: a [Reason:] None
9. How the new states are generated in genetic algorithm?
a) Composition
b) Mutation
c) Cross-over
d) Both Mutation & Cross-over
Answer
Answer: d [Reason:] New states are generated by mutation and by crossover, which combines a pair of states from the population.
10. Which method is effective for escaping from local minima?
a) Updating heuristic estimate
b) Reducing heuristic estimate
c) Eliminating heuristic estimate
d) None of the mentioned
Answer
Answer: a [Reason:] Updating heuristic estimates from experience provides an effective method to escape from local minima.
Artificial Intelligence MCQ Set 4
1. The process by which the brain incrementally orders actions needed to complete a specific task is referred as,
a) Planning problem
b) Partial order planning
c) Total order planning
d) Both Planning problem & Partial order planning
Answer
Answer: b [Reason:] Definition of partial order planning.
2. To complete any task, the brain needs to plan out the sequence by which to execute the behavior. One way the brain does this is with a partial-order plan. State whether true or false.
a) True
b) False
Answer
Answer: a [Reason:] None.
3. In partial order plan.
A. Relationships between the actions of the behavior are set prior to the actions
B. Relationships between the actions of the behavior are not set until absolutely necessary
Choose the correct option.
a) A is true
b) B is true
c) Either A or B can be true depending upon situation
d) Neither A nor B is true
Answer
Answer: a [Reason:] Relationship between behavior and actions is established dynamically.
4. Partial-order planning exhibits the Principle of Least Commitment, which contributes to the efficiency of this planning system as a whole.
a) True
b) False
Answer
Answer: a [Reason:] None.
5. Following is/are the components of the partial order planning.
a) Bindings
b) Goal
c) Causal Links
d) All of the mentioned
Answer
Answer: d [Reason:] Bindings: The bindings of the algorithm are the connections between specific variables in the action. Bindings, as ordering, only occur when it is absolutely necessary.
Causal Links: Causal links in the algorithm are those that categorically order actions. They are not the specific order (1,2,3) of the actions, rather the general order as in Action 2 must come somewhere after Action 1, but before Action 2.
Plan Space: The plan space of the algorithm is constrained between its start and finish. The algorithm starts, producing the initial state and finishes when all parts of the goal is been achieved.
6. Partial-order planning is the opposite of total-order planning.
a) True
b) False
Answer
Answer: a [Reason:] Partial-order planning is the opposite of total-order planning, in which actions are sequenced all at once and for the entirety of the task at hand.
7. Sussman Anomaly can be easily and efficiently solved by partial order planning.
a) True
b) False
Answer
Answer: a [Reason:] http://en.wikipedia.org/wiki/Sussman_Anomaly.
8. Sussman Anomaly illustrates a weakness of interleaved planning algorithm.
a) True
b) False
Answer
Answer: b [Reason:] Sussman Anomaly illustrates a weakness of noninterleaved planning algorithm.
9. One the main drawback of this type of planning system is that it requires a lot of computational powers at each node.
a) True
b) False
Answer
Answer: a [Reason:] None.
10. What are you predicating by the logic: ۷x: €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
Answer
Answer: a [Reason:] ۷x denotes Everyone or all, and €y someone and loyal to is the proposition logic making map x to y.
11. A plan that describe how to take actions in levels of increasing refinement and specificity is
a) Problem solving
b) Planning
c) Non-hierarchical plan
d) Hierarchical plan
Answer
Answer: d [Reason:] A plan that describes how to take actions in levels of increasing refinement and specificity is Hierarchical (e.g., “Do something” becomes the more specific “Go to work,” “Do work,” “Go home.”) Most plans are hierarchical in nature.
12. A constructive approach in which no commitment is made unless it is necessary to do so, is
a) Least commitment approach
b) Most commitment approach
c) Nonlinear planning
d) Opportunistic planning
Answer
Answer: a [Reason:] Because we are not sure about the outcome.
13. Uncertainty arises in the Wumpus world because the agent’s sensors give only
a) Full & Global information
b) Partial & Global Information
c) Partial & local Information
d) Full & local information
Answer
Answer: c [Reason:] The Wumpus world is a grid of squares surrounded by walls, where each square can contain agents and objects. The agent (you) always starts in the lower left corner, a square that will be labeled [1, 1]. The agent’s task is to find the gold, return to [1, 1] and climb out of the cave. Therefore, uncertainty is there as the agent gives partial and local information only. Global variable are not goal specific problem solving.
Artificial Intelligence MCQ Set 5
1. Which of the following search belongs to totally ordered plan search?
a) Forward state-space search
b) Hill-climbing search
c) Depth-first search
d) Breadth-first search
Answer
Answer: a [Reason:] Forward and backward state-space search are particular forms of totally ordered plan search.
2. Which cannot be taken as advantage for totally ordered plan search?
a) Composition
b) State search
c) Problem decomposition
d) None of the mentioned
Answer
Answer: c [Reason:] As the search explore explore only linear sequences of actions, So they cannot take the advantage of problem decomposition.
3. What is the advantage of totally ordered plan in constructing the plan?
a) Reliability
b) Flexibility
c) Easy to use
d) All of the mentioned
Answer
Answer: b [Reason:] Totally ordered plan has the advantage of flexibility in the order in which it constructs the plan.
4. Which strategy is used for delaying a choice during search?
a) First commitment
b) Least commitment
c) Both First & Least commitment
d) None of the mentioned
Answer
Answer: b [Reason:] The general strategy of delaying a choice during search is called a least commitment strategy.
5. Which algorithm place two actions into a plan without specifying which should come first?
a) Full-order planner
b) Total-order planner
c) Semi-order planner
d) Partial-order planner
Answer
Answer: d [Reason:] Any planning algorithm that can place two actions into a plan without specifying which should come first is called partial-order planner.
6. How many possible plans are available in partial-order solution?
a) 3
b) 4
c) 5
d) 6
Answer
Answer: d [Reason:] The partial-order solution corresponds to six possible total-order plans.
7. What is the other name of each and every total-order plans?
a) Polarization
b) Linearization
c) Solarization
d) None of the mentioned
Answer
Answer: b [Reason:] Each and every total order plan is also called as linearization of the partial-order plan.
8. What are present in the empty plan?
a) Start
b) Finish
c) Modest
d) Both Start & Finish
Answer
Answer: d [Reason:] The ’empty’ plan contains just the start and finish actions.
9. What are not present in start actions?
a) Preconditions
b) Effect
c) Finish
d) None of the mentioned
Answer
Answer: a [Reason:] Start has no precondition and has as its effects all the literals in the initial state of the planning problem.
10. What are not present in finish actions?
a) Preconditions
b) Effect
c) Finish
d) None of the mentioned
Answer
Answer: b [Reason:] Finish has no effects and has as its preconditions the goal literals of the planning algorithm.
11. Which can be adapted for planning algorithm?
a) Most-constraint variable
b) Most-constraint literal
c) Constraint
d) None of the mentioned
Answer
Answer: a [Reason:] The most-constraint variable heuristic from CSPs can be adapted for planning algorithm and seems to work well.
