Subject: Artificial Intelligence

Unit 1 : What is AI?

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

Who is the “father” of artificial intelligence?

a) Fisher Ada
b) John McCarthy
c) Allen Newell
d) Alan Turning

What was originally called the “imitation game” by its creator?

a) The Turing Test
b) LISP
c) The Logic Theorist
d) Cybernetics

Which particular generation of computers is associated with artificial intelligence?

a) Second
b) Fourth
c) Fifth
d) Third
A bidirectional feedback loop links computer modeling with _____________
a) artificial science
b) heuristic processing
c) human intelligence
d) cognitive science

What is the name of the computer program that simulates the thought processes of human
beings?
a) Human logic
b) Expert reason
c) Expert system
d) Personal information

What is the name of the computer program that contains the distilled knowledge of an
expert?
a) Database management system
b) Management information System
c) Expert system
d) Artificial intelligence

A computer program that contains expertise in a particular domain is called?

a) intelligent planner
b) automatic processor
c) expert system
d) operational symbolize

A.M. turing developed a technique for determining whether a computer could or could not
demonstrate the artificial Intelligence, Presently, this technique is called __________
a) Turing Test
b) Algorithm
c) Boolean Algebra
d) Logarithm

Which of the following nis task domains of AI?

a) Mundane Task

b) Formal Task

c) Expert Task

d) All of the above

Unit 2: Problems, State Space Search &Heuristic Search Techniques

Which search method takes less memory?

a) Depth-First Search
b) Breadth-First search
c) Optimal search
d) Linear Search

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 is
d) All of the mentioned
The explanation facility of an expert system may be used to __________
a) construct a diagnostic model
b) expedite the debugging process
c) explain the system’s reasoning process
d) expedite the debugging process & explain the system’s reasoning process

Which is the most straightforward approach for planning algorithm?

a) Best-first search
b) State-space search
c) Depth-first search
d) Hill-climbing search

What are taken into account of state-space search?

a) Postconditions
b) Preconditions
c) Effects
d) Both Preconditions & Effects

Explanation: The state-space search takes both precondition and effects into account for solving
a problem.

How many ways are available to solve the state-space search?

a) 1
b) 2
c) 3
d) 4

Explanation: There are two ways available to solve the state-space search. They are forward
from the initial state and backward from the goal.
What is the other name for forward state-space search?
a) Progression planning
b) Regression planning
c) Test planning
d) None of the mentioned

Explanation: It is sometimes called as progression planning, because it moves in the forward

direction.

How many states are available in state-space search?

a) 1
b) 2
c) 3
d) 4

Explanation: There are four states available in state-space search. They are initial state, actions,
goal test and step cost.

What is the main advantage of backward state-space search?

a) Cost
b) Actions
c) Relevant actions
d) All of the mentioned

Explanation: The main advantage of backward search will allow us to consider only relevant
actions.

What is the other name of the backward state-space search?

a) Regression planning
b) Progression planning
c) State planning
d) Test planning
Explanation: Backward state-space search will find the solution from goal to the action, So it is
called as Regression planning.

Which approach is to pretend that a pure divide and conquer algorithm will work?
a) Goal independence
b) Subgoal independence
c) Both Goal & Subgoal independence
d) None of the mentioned

Explanation: Subgoal independence approach is to pretend that a pure divide and conquer
algorithm will work for admissible heuristics.

Which term is used for describing the judgmental or commonsense part of problem
solving?
a) Heuristic
b) Critical
c) Value based
d) Analytical

Which of the following, is a component of an expert system?

a) inference engine
b) knowledge base
c) user interface
d) all of the mentioned

The explanation facility of an expert system may be used to __________

a) construct a diagnostic model
b) expedite the debugging process
c) explain the system’s reasoning process
d) expedite the debugging process & explain the system’s reasoning process
What is the main task of a problem-solving agent?
a) Solve the given problem and reach to goal
b) To find out which sequence of action will get it to the goal state
c) All of the mentioned
d) None of the mentioned

Explanation: The problem-solving agents are one of the goal-based agents.

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

Explanation: Because state space is mostly concerned with a problem, when you try to solve a
problem, we have to design a mathematical structure to the problem, which can only be through
variables and parameters. eg. You have given a 4-gallon jug and another 3-gallon jug. Neither
has measuring marker on it. You have to fill the jugs with water. How can you get exactly 2
gallons of water in to 4 gallons. Here the state space can defined as set of ordered pairs
integers(x,y), such that x=0,1,2,3 or 4 and y=0,1,2 or 3; X represents the number of gallons in 4
gallon jug and y represents the quantity of water in the 3-gallon jug.

A search algorithm takes _________ as an input and returns ________ as an output.

a) Input, output
b) Problem, solution
c) Solution, problem
d) Parameters, sequence of actions

Explanation: A search algorithm takes input as a problem and returns a solution to the problem
as an output.
A problem in a search space is defined by one of these state.
a) Initial state
b) Last state
c) Intermediate state
d) All of the mentioned

Explanation: A problem has four components initial state, goal test, set of actions, path cost.

The Set of actions for a problem in a state space is formulated by a ___________

a) Intermediate states
b) Initial state
c) Successor function, which takes current action and returns next immediate state
d) None of the mentioned

Explanation: The most common formulation for actions uses a successor function. Given a
particular state x, SUCCESSOR-FN(x) returns a set of (action, successor) ordered pairs, where
each action is one of the legal actions in state x and each successor is a state that can be reached
from x by applying the action.

The _______ is a touring problem in which each city must be visited exactly once. The aim
is to find the shortest tour.
a) Finding shortest path between a source and a destination
b) Travelling Salesman problem
c) Map coloring problem
d) Depth first search traversal on a given map represented as a graph

What is the major component/components for measuring the performance of problem

solving?
a) Completeness
b) Optimality
c) Time and Space complexity
d) All of the mentioned

Explanation: For best performance consideration of all component is necessary.

A production rule consists of ____________

a) A set of Rule
b) A sequence of steps
c) Set of Rule & sequence of steps
d) Arbitrary representation to problem

Explanation: When you are trying to solve a problem, you should design how to get a step-by-
step solution with constraints condition to your problem, e.g Chess board problem.

Which search method takes less memory?

a) Depth-First Search
b) Breadth-First search
c) Linear Search
d) Optimal search

Explanation: Depth-First Search takes less memory since only the nodes on the current path are

stored, but in Breadth First Search, all of the tree that has generated must be stored.

Which search strategy is also called as blind search?

a) Uninformed search
b) Informed search
c) Simple reflex search
d) All of the mentioned

Explanation: In blind search, We can search the states without having any additional
information. So uninformed search method is blind search.
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

Explanation: Because of FIFO queue, it will assure that the nodes that are visited first will be
expanded first.

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

Explanation: Because it always expands the shallowest unexpanded node.

How many parts does a problem consists of?

a) 1
b) 2
c) 3
d) 4

Explanation: The four parts of the problem are initial state, set of actions, goal test and path cost.

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
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

Explanation: It implements stack operation because it always expands the deepest node in the
current tree.

What is the other name of informed search strategy?

a) Simple search
b) Heuristic search
c) Online search
d) None of the mentioned

Explanation: A key point of informed search strategy is heuristic function, So it is called as

heuristic function.

What is the heuristic function of greedy best-first search?

a) f(n) != h(n)
b) f(n) < h(n)
c) f(n) = h(n)
d) f(n) > h(n)

Which function will select the lowest expansion node at first for evaluation?
a) Greedy best-first search
b) Best-first search
c) Depth-first search
d) None of the mentioned

Explanation: The lowest expansion node is selected because the evaluation measures distance to
the goal.
Which search is complete and optimal when h(n) is consistent?
a) Best-first search
b) Depth-first search
c) Both Best-first & Depth-first search
d) A* search

Which is used to improve the performance of heuristic search?

a) Quality of nodes
b) Quality of heuristic function
c) Simple form of nodes
d) None of the mentioned

Explanation: Good heuristic can be constructed by relaxing the problem, So the performance of
heuristic search can be improved.

Which search method will expand the node that is closest to the goal?
a) Best-first search
b) Greedy best-first search
c) A* search
d) None of the mentioned

Explanation: Because of using greedy best-first search, It will quickly lead to the solution of the
problem.

A* algorithm is based on ___________

a) Breadth-First-Search
b) Depth-First –Search
c) Best-First-Search
d) Hill climbing
Explanation: Best-first-search is giving the idea of optimization and quick choose of path, and all
these characteristic lies in A* algorithm.

The search strategy the uses a problem specific knowledge is known as ___________.
a) Informed Search
b) Best First Search
c) Heuristic Search
d) All of the mentioned

Explanation: The problem specific knowledge is also known as Heuristics and Best-First search
uses some heuristic to choose the best node for expansion.

Best-First search can be implemented using the following data structure.

a) Queue
b) Stack
c) Priority Queue
d) Circular Queue

Explanation: Best-first search can be implemented within our general search framework via a
priority queue, a data structure that will maintain the fringe in ascending order of f-values.

Best-First search is a type of informed search, which uses ________________ to choose the
best next node for expansion.
a) Evaluation function returning lowest evaluation
b) Evaluation function returning highest evaluation
c) Evaluation function returning lowest & highest evaluation
d) None of them is applicable

Explanation: Best-first search is an instance of the general TREE-SEARCH or GRAPH-

SEARCH algorithm in which a node is selected for expansion based on an evaluation function, f
(n). Traditionally, the node with the lowest evaluation is selected for expansion, because the
evaluation measures distance to the goal.
Heuristic function h(n) is ________
a) Lowest path cost
b) Cheapest path from root to goal node
c) Estimated cost of cheapest path from root to goal node
d) Average path cost

Explanation: Heuristic is an estimated cost.

What is the evaluation function in greedy approach?

a) Heuristic function
b) Path cost from start node to current node
c) Path cost from start node to current node + Heuristic cost
d) Average of Path cost from start node to current node and Heuristic cost

What is the evaluation function in A* approach?

a) Heuristic function
b) Path cost from start node to current node
c) Path cost from start node to current node + Heuristic cost
d) Average of Path cost from start node to current node and Heuristic cost

Explanation: The most widely-known form of best-first search is called A* search. It evaluates
nodes by combining g(n), the cost to reach the node, and h(n.), the cost to get from the node to
the goal: f(n) = g(n) + h(n). Since g(n) gives the path cost from the start node to node n, and h(n)
is the estimated cost of the cheapest path from n to the goal.

What are the main cons of hill-climbing search?

a) Terminates at local optimum & Does not find optimum solution
b) Terminates at global optimum & Does not find optimum solution
c) Does not find optimum solution & Fail to find a solution
d) Fail to find a solution
Explanation: Algorithm terminates at local optimum values, hence fails to find optimum
solution.

Hill-Climbing approach stuck for which of the following reasons?

a) Local maxima
b) Ridges
c) Plateaux
d) All of the mentioned

Explanation: Local maxima: a local maximum is a peak that is higher than each of its
neighboring states, but lower than the global maximum. Ridges: Ridges result in a sequence of
local maxima that is very difficult for greedy algorithms to navigate. Plateaux: a plateau is an
area of the state space landscape where the evaluation function is flat.

The term ___________ is used for a depth-first search that chooses values for one variable
at a time and returns when a variable has no legal values left to assign.
a) Forward search
b) Backtrack search
c) Hill algorithm
d) Reverse-Down-Hill search

Explanation: Refer definition of backtracking algorithm.

Backtracking is based on ____________.

a) Last in first out
b) First in first out
c) Recursion
d) Both Last in first out & Recursion

Explanation: Recursion uses LIFO.

_________________ are mathematical problems defined as a set of objects whose state must
satisfy a number of constraints or limitations.
a) Constraints Satisfaction Problems
b) Uninformed Search Problems
c) Local Search Problems
d) All of the mentioned

Which of the Following problems can be modeled as CSP?

a) 8-Puzzle problem
b) 8-Queen problem
c) Map coloring problem
d) All of the mentioned

Explanation: All of above problems involves constraints to be satisfied.

Consider a problem of preparing a schedule for a class of student. What type of problem is
this?
a) Search Problem
b) Backtrack Problem
c) CSP
d) Planning Problem

Explanation: Schedule developer needs to consider all constraints on teacher as well as students.

Which of the following is AI problem characteristics?

Is the problem decomposable?

Can solution steps be ignore or undone?

Is the solution absolute or relative?

All of the above.

Which of the following is requirement for good control strategy?

It should be systematic.

It should cause motion.

Both of these.

None of these.

Chess is an example of ____________.

Recoverable problem

Irrecoverable problem

Ignorable problem

None of the above.

8-puzzle is an example of _______.

Recoverable problem

Irrecoverable problem

Ignorable problem

None of the above.

A ________is a state that is better than all its neighbors but is not better than some other
states farther away.

Local Maximul

Plateau
Ridge

Resolution

A ______ is a flat area of the search space in which a whole set of neighboring states have
the same value.

Local Maximul

Plateau

Ridge

Resolution

A___________is an area of the search space that is higher than surrounding areas and that
itself has a slop.

Local Maximul

Plateau

Ridge

Resolution

__________is a variation of hill climbing in which, at the beginning of the process, some
downhill moves may be made.

Simulated Annealing

Local Maximam

Plateau

Resolution
The _______analysis process centers around the detection of differences between the
current state and the goal state.

Means-ends analysis

Local Maximam

Plateau

Resolution

_______consider all moves from the current state and selects the best one as the next state.

Steepest ascent hill climbing

Simple hill climbing

Both of these

None of these

Unit 3: Knowledge Representation Issues

Ability to represent all of the kinds of knowledge that are needed in the domain is
called_____________.

Representational Adequacy

Inferential Adequacy

Inferential Efficiency

Acquisitional Efficiency
_________is the ability to incorporate into the knowledge structure additional information
that can be used to focus the attention of the inference mechanisms in the most promising
directions.

Representational Adequacy

Inferential Adequacy

Inferential Efficiency

Acquisitional Efficiency

The ability to acquire new informational easily is called__________.

Representational Adequacy

Inferential Adequacy

Inferential Efficiency

Acquisitional Efficiency

Consider a good system for the representation of knowledge in a particular domain. What
property should it possess?
a) Representational Adequacy
b) Inferential Adequacy
c) Inferential Efficiency
d) All of the mentioned

Explanation: Consider a good system for the representation of knowledge in a particular domain.
The properties should be Representational Adequacy, Inferential Adequacy, Inferential
Efficiency and Acquisitional Efficiency.
__________is the ability to manipulate the representational structures in such a way as to
derive the new structures corresponding to new knowledge inferred from old.

Representational Adequacy

Inferential Adequacy

Inferential Efficiency

Acquisitional Efficiency

A good system for knowledge representation in a particular domain should possess which
of the following property?

Representational Adequacy

Inferential Adequacy

Inferential Efficiency

All of these

Which of the following is knowledge representation technique?

Simple relational technique

Inheritable knowledge

Inferential knowledge

All of these
Unit4: Using Predicate Logic

Two literals are complementary if _____________.

a) They are equal
b) They are identical and of equal sign
c) They are identical but of opposite sign
d) They are unequal but of equal sign

Explanation: Two literals are complementary if they are identical but of opposite sign

_______technique uses proofs by contradictions.

Resolution

Backward Chaining

Unification

None of these

_________ is a process of making two different logical atomic expressions identical by

finding a substitution.

Resolution

Backward Chaining

Unification

None of these
Unit5: Representing Knowledge Using Rules

A ________is one in which knowledge is specified, but the use to which that knowledge is to
be put is not given.

Declarative representation

Procedural representation

Both of these

None of these

A PROLOG program is described as a series of logical assertions, each of which is a

___________.

Horn clause

Unification

Resolution

Backward Chaining

Reasoning process from start to goal state is referred to as__________.

Forward reasoning

Backward reasoning

None of these

Both of these

Reasoning process from goal to start is referred to as_________.

Forward reasoning
Backward reasoning

None of these

Both of these

PROLOG is an example of ____________.

Backward chaining rule system

Forward chaining rule system

None of these

Both of these

Unit6: Symbolic Reasoning under Uncertainty

What is another type of Default reasoning?

a) Monotonic reasoning
b) Analogical reasoning
c) Bitonic reasoning
d) Non-monotonic reasoning

Explanation: Default reasoning is another type of non-monotonic reasoning.

A logic is _________ if some conclusions can be invalidated by adding more knowledge.

a) Monotonic
b) Analogical
c) Bitonic
d) Non-monotonic
In ___________, once the conclusion is taken, then it will remain the same even if we add
some other information to existing information in our knowledge base.

a) Monotonic reasoning
b) Analogical reasoning
c) Bitonic reasoning
d) Non-monotonic reasoning

__________is a form of nonmonotonic reasoning where plausible conclusions are inferred

based on general rules which may have exceptions.

Default reasoning

Monotonic reasoning

Analogical reasoning
Bitonic reasoning

In default logic, which of the following inference rules of the form is allowed?
a) (A : B) / C
b) A / (B : C)
c) A / B
d) A / B : C

Explanation: In default logic, we allow inference rules of the form:(A : B) / C.

Unit 7: Statistical Reasoning

Which of the following is true in Statistical reasoning?

a) The representation is extended to allow some kind of numeric measure of certainty to be
associated with each statement
b) The representation is extended to allow ‘TRUE or FALSE’ to be associated with each
statement
c) The representation is extended to allow some kind of numeric measure of certainty to be
associated common to all statements
d) The representation is extended to allow ‘TRUE or FALSE’ to be associated common to all
statements

Explanation: Statistical reasoning is the representation is extended to allow some kind of

numeric measure of certainty to be associated with each statement.

________is used to calculate the probability of an event based on its association with
another event.

Bayes theorem

Resolution

Unification

Backward chining

A ________ is a probabilistic graphical model which represents a set of variables and their
conditional dependencies using a directed acyclic graph.

Bayesian network

Resolution

Unification

Backward chining

The theory of belief functions or evidence theory is referred to as_________.

Dempster Shafer theory

Bayesian network
Resolution

Unification

In Bayes theorem, what is meant by P(Hi|E)?

a) The probability that hypotheses Hi is true given evidence E
b) The probability that hypotheses Hi is false given evidence E
c) The probability that hypotheses Hi is true given false evidence E
d) The probability that hypotheses Hi is false given false evidence E

Explanation: In Bayes theorem, P(Hi|E) is the probability that hypotheses Hi is true given
evidence E.

Unit 8: Weak Slot and Filler Structures

In _______information is represented as a set of nodes connected to each other by a set of

labeled arcs.

Semantic net

Bayesian network

Resolution

Unification

Hierarchies that are not tree is called ___________.

Tangled Hierarchy

Bayesian network

Resolution

Unification
Unit 9: Strong Slot and Filler Structure

________ is a theory of how to represent the kind of knowledge about events that is usually
contained in natural language sentences.

Conceptual dependency

Script

Tangled Hierarchy

Bayesian network

A _________is a structure that describes a stereotyped sequence of events in a particular

context.

Conceptual dependency

Script

Tangled Hierarchy

Bayesian network

Which of the following is component of script?

Entry conditions

Result

Roles

All of these
Unit 10: Game Playing

Which search is equal to minimax search but eliminates the branches that can’t influence
the final decision?
a) Depth-first search
b) Breadth-first search
c) Alpha-beta pruning
d) None of the mentioned

Explanation: The alpha-beta search computes the same optimal moves as minimax, but
eliminates the branches that can’t influence the final decision.

Which values are independant in minimax search algorithm?

a) Pruned leaves x and y
b) Every states are dependant
c) Root is independant
d) None of the mentioned

Explanation: The minimax decision are independant of the values of the pruned values x and y
because of the root values.

To which depth does the alpha-beta pruning can be applied?

a) 10 states
b) 8 States
c) 6 States
d) Any depth

Explanation: Alpha–beta pruning can be applied to trees of any depth and it is possible to prune
entire subtree rather than leaves.
Which search is similar to minimax search?
a) Hill-climbing search
b) Depth-first search
c) Breadth-first search
d) All of the mentioned

Explanation: The minimax search is depth-first search, So at one time we just have to consider
the nodes along a single path in the tree.

Which value is assigned to alpha and beta in the alpha-beta pruning?

a) Alpha = max
b) Beta = min
c) Beta = max
d) Both Alpha = max & Beta = min

Explanation: Alpha and beta are the values of the best choice we have found so far at any choice
point along the path for MAX and MIN.

Where does the values of alpha-beta search get updated?

a) Along the path of search
b) Initial state itself
c) At the end
d) None of the mentioned

Explanation: Alpha-beta search updates the value of alpha and beta as it gets along and prunes
the remaining branches at node.

How the effectiveness of the alpha-beta pruning gets increased?

a) Depends on the nodes
b) Depends on the order in which they are executed
c) All of the mentioned
d) None of the mentioned
Explanation: None.

Which function is used to calculate the feasibility of whole game tree?

a) Evaluation function
b) Transposition
c) Alpha-beta pruning
d) All of the mentioned

Explanation: Because we need to cut the search off at some point and apply an evaluation
function that gives an estimate of the utility of the state.

Which kind of planning consists of successive representations of different levels of a plan?

a) hierarchical planning
b) non-hierarchical planning
c) project planning
d) all of the mentioned

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

a) Linear approach
b) Heuristic approach (Some knowledge is stored)
c) Random approach
d) An Optimal approach

Explanation: We use a Heuristic approach, as it will find out brute force computation, looking at
hundreds of thousands of positions. e.g Chess competition between Human and AI based
Computer.

Third component of a planning system is to ___________

a) Detect when a solution has been found
b) Detect when solution will be found
c) Detect whether solution exists or not
d) Detect whether multiple solutions exist

Explanation: Third component of a planning system is to detect when a solution has been found.

Which of the following is component of a planning system?

Choosing rules to apply

Applying rules

Detecting a solution

All of these

Unit 11: Understanding

To ______ something is to transform it from one representation into another.

Understanding

Choosing rules to apply

Applying rules

Detecting a solution

Which of the following factor makes understanding hard?

Complexity of the target representation

Type of mapping

Level of interaction among components

All of these
__________ is the process of interpreting an input and assigning it meaning.

Understanding

Choosing rules to apply

Applying rules

Detecting a solution

Unit12: Natural Language Processing

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

Which of the following is part of NLP?

Morphological Analysis

Syntactic Analysis

Semantic Analysis

All of these

Individual words are analyzed into their components is referred to as___________.

Morphological Analysis

Syntactic Analysis
Semantic Analysis

Pragmatic Analysis

Parse tree is constructed in _______________steps of NLP.

Morphological Analysis

Syntactic Analysis

Semantic Analysis

Pragmatic Analysis

The structures created by the syntactic analyzer are assigned meanings. This is called
_______.

Morphological Analysis

Syntactic Analysis

Semantic Analysis

Pragmatic Analysis

The meaning of an individual sentence may depend on the sentences that precedes it and
may influence the meanings of the sentence s that follow it. This is called___________.

Morphological Analysis

Syntactic Analysis

Discourse Integration

Pragmatic Analysis

The structure representing what was actually said is reinterpreted to determine what was
actually meant. This is called__________.
Morphological Analysis

Syntactic Analysis

Discourse Integration

Pragmatic Analysis

Which of the following is a way of handling sentences correctly?

All paths

Best path with backtracking

Best path with patchup

All of these

_________is a top down parsing procedure that allows various kinds of knowledge to be
incorporated into it.

ATN

Morphological Analysis

Syntactic Analysis

Discourse Integration

Unit 13: Connectionist Models

Research scientists all over the world are taking steps towards building computers with
circuits patterned after the complex interconnections existing among the human brain’s
nerve cells. What name is given to such type of computers?
a) Intelligent computers
b) Supercomputers
c) Neural network computers
d) Smart computers

______have a scalar value associated with each neuron of the network that resembles the
notion of energy.

Hopfield networks

Perceptron

Neural network

Supercomputers

Which of the following is feature of Hopfield network?

Distributed representation

Distributed asynchronous control

Content addressable memory

All of these

The _______ was one of the earliest neural network models.

Hopfield networks

Perceptron

Neural network

Supercomputers

In __________, teacher is present during learning process and present expected output.

Supervised learning
Unsupervised learning

Reinforced learning

Competitive learning

In ______, teacher is not present and desired output is not presented to the network.

Supervised learning

Unsupervised learning

Reinforced learning

Competitive learning

In _________, teacher is present but does not present the expected output.

Supervised learning

Unsupervised learning

Reinforced learning

Competitive learning

__________strategy is called “winner-takes-all”.

Supervised learning

Unsupervised learning

Reinforced learning

Competitive learning

Which of the following is an application of neural network?

Clustering
Classification

Function approximation

All of these

A __________network has atleast one feedback loop.

Recurrent network

Feed forward network

Both of these

None of the above

Unit 14: Introduction to Prolog

A process that is repeated, evaluated, and refined is called __________

a) diagnostic
b) descriptive
c) interpretive
d) iterative

PROLOG is an AI programming language, which solves problems with a form of symbolic

logic known as predicate calculus. It was developed in 1972 at the University of Marseilles
by a team of specialists. Can you name the person who headed this team?
a) Alain Colmerauer
b) Niklaus Wirth
c) Seymour Papert
d) John McCarthy
Which predicate is used for recursion in prolog?

Repeat

Cut

Fail

None of the above

Prolog is ___________.

Object Oriented Language

Procedural Language

None of the above

Both of these

Which of the following is not an application of prolog?

Robotics

Natural Language Processing

Expert System

All of the above

Which of the following object is available in prolog?

Char

Integer

String

All of the above

The __________predicate offers a way to control backtracking.

Repeat

Cut

Fail

All of the above

The entire expression before the period in each case is called a _________.

Domain

Predicate

Clause

None of the above

Language/Languages used for programming Constraint Programming includes

____________.
a) Prolog
b) C#
c) C
d) Fortrun