250+ TOP MCQs on Neural Networks – 2 and Answers

AI Multiple Choice Questions on “Neural Networks – 2”.

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.
Answer: d
Clarification: 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
Answer: c
Clarification: 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
Answer: b
Clarification: 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
Answer: a
Clarification: 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
Answer: a
Clarification: 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
Answer: a
Clarification: Yes the perceptron works like that.

7. What is the name of the function in the following statement “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) Step function
b) Heaviside function
c) Logistic function
d) Perceptron function
Answer: b
Clarification: 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
Answer: c
Clarification: None.

9. The network that involves backward links from output to the input and hidden layers is called _________
a) Self organizing maps
b) Perceptrons
c) Recurrent neural network
d) Multi layered perceptron
Answer: c
Clarification: 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
Answer: d
Clarification: All mentioned options are applications of Neural Network.

250+ TOP MCQs on Frames and Answers

Artificial Intelligence Multiple Choice Questions on “Frames”.

1. What is the frame?
a) A way of representing knowledge
b) Data Structure
c) Data Type
d) None of the mentioned
Answer: a
Clarification: None.

2. Frames in artificial intelligence is derived from semantic nets.
a) True
b) False
Answer: a
Clarification: A frame is an artificial intelligence data structure used to divide knowledge into substructures by representing “stereotyped situations.”.

3. Which of the following elements constitutes the frame structure?
a) Facts or Data
b) Procedures and default values
c) Frame names
d) Frame reference in hierarchy
Answer: a
Clarification: None.

4. Like semantic networks, frames can be queried using spreading activation.
a) True
b) False
Answer: a
Clarification: None.

5. What is Hyponymy relation?
a) A is part of B
b) B has A as a part of itself
c) A is subordinate of B
d) A is superordinate of B
Answer: c
Clarification: In linguistics, a hyponym is a word or phrase whose semantic field is included within that of another word, its hypernym (sometimes spelled hypernym outside of the natural language processing community). In simpler terms, a hyponym shares a type-of relationship with its hypernym.

6. The basic inference mechanism in semantic network in which knowledge is represented as Frames is to follow the links between the nodes.
a) True
b) False
Answer: a
Clarification: None.

7. There exists two way to infer using semantic networks in which knowledge is represented as Frames.
1) Intersection Search
2) Inheritance Search
a) True
b) False
Answer: a
Clarification: None.

250+ TOP MCQs on Local Search Problems and Optimization Problems and Answers

Artificial Intelligence Questions and Answers for Campus interviews on “Local Search Problems and Optimization Problems”.

1. In many problems the path to goal is irrelevant, this class of problems can be solved using ____________
a) Informed Search Techniques
b) Uninformed Search Techniques
c) Local Search Techniques
d) Informed & Uninformed Search Techniques
Answer: c
Clarification: If the path to the goal does not matter, we might consider a different class of algorithms, ones that do not worry about paths at all. Local search algorithms operate using a single current state (rather than multiple paths) and generally move only to neighbors of that state.

2. Though local search algorithms are not systematic, key advantages would include __________
a) Less memory
b) More time
c) Finds a solution in large infinite space
d) Less memory & Finds a solution in large infinite space
Answer: d
Clarification: Two advantages: (1) they use very little memory-usually a constant amount; and (2) they can often find reasonable solutions in large or infinite (continuous) state spaces for which systematic algorithms are unsuitable.

3. A complete, local search algorithm always finds goal if one exists, an optimal algorithm always finds a global minimum/maximum.
a) True
b) False
Answer: a
Clarification: An algorithm is complete if it finds a solution if exists and optimal if finds optimal goal (minimum or maximum).

4. _______________ Is an algorithm, a loop that continually moves in the direction of increasing value – that is uphill.
a) Up-Hill Search
b) Hill-Climbing
c) Hill algorithm
d) Reverse-Down-Hill search
Answer: b
Clarification: Refer the definition of Hill-Climbing approach.

5. When will Hill-Climbing algorithm terminate?
a) Stopping criterion met
b) Global Min/Max is achieved
c) No neighbor has higher value
d) All of the mentioned
Answer: c
Clarification: When no neighbor is having higher value, algorithm terminates fetching local min/max.

6. 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
Answer: a
Clarification: Algorithm terminates at local optimum values, hence fails to find optimum solution.

7. Stochastic hill climbing chooses at random from among the uphill moves; the probability of selection can vary with the steepness of the uphil1 move.
a) True
b) False
Answer: a
Clarification: Refer to the definition of variants of hill-climbing search.

8. Hill climbing sometimes called ____________ because it grabs a good neighbor state without thinking ahead about where to go next.
a) Needy local search
b) Heuristic local search
c) Greedy local search
d) Optimal local search
Answer: c
Clarification: None.

9. Hill-Climbing approach stuck for which of the following reasons?
a) Local maxima
b) Ridges
c) Plateaux
d) All of the mentioned
Answer: d
Clarification: 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.

10. ___________ algorithm keeps track of k states rather than just one.
a) Hill-Climbing search
b) Local Beam search
c) Stochastic hill-climbing search
d) Random restart hill-climbing search
Answer: b
Clarification: Refer to the definition of Local Beam Search algorithm.

11. A genetic algorithm (or GA) is a variant of stochastic beam search in which successor states are generated by combining two parent states, rather than by modifying a single state.
a) True
b) False
Answer: a
Clarification: Stochastic beam search, analogous to stochastic hill climbing, helps to alleviate this problem. Instead of choosing the best k from the pool of candidate successors, stochastic beam search chooses k successors at random, with the probability of choosing a given successor being an increasing function of its value.

12. What are the two main features of Genetic Algorithm?
a) Fitness function & Crossover techniques
b) Crossover techniques & Random mutation
c) Individuals among the population & Random mutation
d) Random mutation & Fitness function
Answer: a
Clarification: Fitness function helps choosing individuals from the population and Crossover techniques defines the offspring generated.

13. Searching using query on Internet is, use of ___________ type of agent.
a) Offline agent
b) Online agent
c) Both Offline & Online agent
d) Goal Based & Online agent
Answer: d
Clarification: Refer to the definitions of both the type of agent.

Global Education & Learning Series – Artificial Intelligence.

250+ TOP MCQs on Artificial Intelligence Agents and Answers

Artificial Intelligence Multiple Choice Questions on “Artificial Intelligence Agents”.

1. The performance of an agent can be improved by __________
a) Learning
b) Observing
c) Perceiving
d) None of the mentioned
Answer: a
Clarification: An agent can improve by saving the previous states on which it was earlier, hence in future it can learn to respond in the same situation better.

2. External actions of the agent is selected by __________
a) Perceive
b) Performance
c) Learning
d) Actuator
Answer: b
Clarification: It depends on how you want to improve and what the performance measures are.

3. The action of the Simple reflex agent completely depends upon __________
a) Perception history
b) Current perception
c) Learning theory
d) Utility functions
Answer: b
Clarification: These agents select actions based on the current perception, ignoring the rest of the perception history.

4. Which of the following could be the approaches to Artificial Intelligence?
a) Strong Artificial Intelligence
b) Weak Artificial Intelligence
c) Applied Artificial Intelligence
d) All of the mentioned
Answer: d
Clarification: Strong Artificial Intelligence aims to build machines that can truly reason and solve problems.
Weak Artificial Intelligence deals with the creation of some form of computer-based artificial intelligence that cannot truly reason and solve problems, but can act as if it were intelligent.
Applied Artificial Intelligence aims to produce commercially viable “smart” systems.
In the Cognitive Artificial Intelligence approach, a computer is used to test theories about how the human mind works.

5. An Artificial Neural Network Is based on?
a) Strong Artificial Intelligence approach
b) Weak Artificial Intelligence approach
c) Cognitive Artificial Intelligence approach
d) Applied Artificial Intelligence approach
Answer: c
Clarification: In the Cognitive Artificial Intelligence approach, a computer is used to test theories about how the human mind works, for example, theories about how we recognize faces and other objects, or about how we solve abstract problems.

6. The Face Recognition system is based on?
a) Strong Artificial Intelligence approach
b) Weak Artificial Intelligence approach
c) Cognitive Artificial Intelligence approach
d) Applied Artificial Intelligence approach
Answer: d
Clarification: Applied Artificial Intelligence approach aims to produce commercially viable “smart” systems such as, for example, a security system that is able to recognize the faces of people who permitted to enter a particular building. Applied Artificial Intelligence has already enjoyed considerable success.

7. A completely automated chess engine (Learn from previous games) is based on?
a) Strong Artificial Intelligence approach
b) Weak Artificial Intelligence approach
c) Cognitive Artificial Intelligence approach
d) Applied Artificial Intelligence approach
Answer: a
Clarification: Strong Artificial Intelligence aims to build machines that can truly reason and solve problems. These machines must be self-aware and their overall intellectual ability needs to be indistinguishable from that of a human being. Strong Artificial Intelligence maintains that suitably programmed machines are capable of cognitive mental states.

8. A basic line following robot is based on __________
a) Strong Artificial Intelligence approach
b) Weak Artificial Intelligence approach
c) Cognitive Artificial Intelligence approach
d) Applied Artificial Intelligence approach
Answer: b
Clarification: Weak Artificial Intelligence deals with the creation of some form of computer-based artificial intelligence that cannot truly reason and solve problems, but can act as if it were intelligent. Weak Artificial Intelligence holds that suitably programmed machines can simulate human cognition.

9. Which of the following task/tasks Artificial Intelligence could not do yet?
a) Understand natural language robustly
b) Web mining
c) Construction of plans in real time dynamic systems
d) All of the mentioned
Answer: d
Clarification: These are the areas in which need more focus for improvements.

10. What among the following is/are the example of the intelligent agent/agents?
a) Human
b) Robot
c) Autonomous Spacecraft
d) All of the mentioned
Answer: d
Clarification: Humans can be looked upon as agents. They have eyes, ears, skin, taste buds, etc. for sensors; and hands, fingers, legs, mouth for effectors. Robots are agents. Robots may have camera, sonar, infrared, bumper, etc. for sensors. They can have grippers, wheels, lights, speakers, etc. for actuators. Autonomous Spacecraft takes decision on its own based on perceptions.

250+ TOP MCQs on Artificial Intelligence Learning and Answers

Artificial Intelligence online test on “Learning – 3”.

1. Which is not a desirable property of a logical rule-based system?
a) Locality
b) Attachment
c) Detachment
d) Truth-Functionality

Answer: b
Clarification: Locality: In logical systems, whenever we have a rule of the form A => B, we can conclude B, given evidence A, without worrying about any other rules. Detachment: Once a logical proof is found for a proposition B, the proposition can be used regardless of how it was derived .That is, it can be detachment from its justification. Truth-functionality: In logic, the truth of complex sentences can be computed from the truth of the components. However, there are no Attachment properties lies in a Rule-based system. Global attribute defines a particular problem space as user specific and changes according to user’s plan to problem.

2. How is Fuzzy Logic different from conventional control methods?
a) IF and THEN Approach
b) FOR Approach
c) WHILE Approach
d) DO Approach

Answer: a
Clarification: FL incorporates a simple, rule-based IF X AND Y THEN Z approach to a solving control problem rather than attempting to model a system mathematically.

3. In an Unsupervised learning ____________
a) Specific output values are given
b) Specific output values are not given
c) No specific Inputs are given
d) Both inputs and outputs are given

Answer: b
Clarification: The problem of unsupervised learning involves learning patterns in the input when no specific output values are supplied. We cannot expect the specific output to test your result. Here the agent does not know what to do, as he is not aware of the fact what propose system will come out. We can say an ambiguous un-proposed situation.

4. Inductive learning involves finding a __________
a) Consistent Hypothesis
b) Inconsistent Hypothesis
c) Regular Hypothesis
d) Irregular Hypothesis

Answer: a
Clarification: Inductive learning involves finding a consistent hypothesis that agrees with examples. The difficulty of the task depends on the chosen representation.

5. Computational learning theory analyzes the sample complexity and computational complexity of __________
a) Unsupervised Learning
b) Inductive learning
c) Forced based learning
d) Weak learning

Answer: b
Clarification: Computational learning theory analyzes the sample complexity and computational complexity of inductive learning. There is a tradeoff between the expressiveness of the hypothesis language and the ease of learning.

6. If a hypothesis says it should be positive, but in fact, it is negative, we call it __________
a) A consistent hypothesis
b) A false negative hypothesis
c) A false positive hypothesis
d) A specialized hypothesis

Answer: c
Clarification: Consistent hypothesis go with examples, If the hypothesis says it should be negative but infect it is positive, it is false negative. If a hypothesis says it should be positive, but in fact, it is negative, it is false positive. In a specialized hypothesis we need to have certain restrict or special conditions.

7. Neural Networks are complex ______________with many parameters.
a) Linear Functions
b) Nonlinear Functions
c) Discrete Functions
d) Exponential Functions

Answer: b
Clarification: Neural networks parameters can be learned from noisy data and they have been used for thousands of applications, so it varies from problem to problem and thus use nonlinear functions.

8. A perceptron is a ______________
a) Feed-forward neural network
b) Backpropagation algorithm
c) Backtracking algorithm
d) Feed Forward-backward algorithm

Answer: a
Clarification: A perceptron is a Feed-forward neural network with no hidden units that can be representing only linear separable functions. If the data are linearly separable, a simple weight updated rule can be used to fit the data exactly.

9. Which of the following statement is true?
a) Not all formal languages are context-free
b) All formal languages are Context free
c) All formal languages are like natural language
d) Natural languages are context-oriented free

Answer: a
Clarification: Not all formal languages are context-free.

10. Which of the following statement is not true?
a) The union and concatenation of two context-free languages is context-free
b) The reverse of a context-free language is context-free, but the complement need not be
c) Every regular language is context-free because it can be described by a regular grammar
d) The intersection two context-free languages is context-free

Answer: d
Clarification: The union and concatenation of two context-free languages are context-free; but intersection need not be.

250+ TOP MCQs on Semantic Net – 2 and Answers

Artificial Intelligence (AI) Question Bank on “Semantic Net – 2”.

1. Which of the following is an extension of the semantic network?
a) Expert Systems
b) Rule Based Expert Systems
c) Decision Tree Based networks
d) Partitioned Networks
Answer: d
Clarification: None.

2. Basic idea of an partitioned nets is to break network into spaces which consist of groups of nodes and arcs and regard each space as a node.
a) True
b) False
Answer: a
Clarification: None.

3. Semantic Network represents _____________
a) Syntactic relation between concepts
b) Semantic relations between concepts
c) All of the mentioned
d) None of the mentioned
Answer: b
Clarification: None.

4. A semantic network is used when one has knowledge that is best understood as a set of concepts that are related to one another.
a) True
b) False
Answer: a
Clarification: None.

5. What are the limitations of the semantic networks?
a) Intractability
b) Lack in expressing some of the properties
c) Incomplete
d) Has memory constraints
Answer: b
Clarification: None.

6. What among the following is/are the best example of semantic networks?
a) Wordnet
b) Human Food Chain
c) MYSIN
d) Autonomous car driver
Answer: a
Clarification: Wordnet is a lexical database of English.

7. Semantic Network is also known as Frame networks.
a) True
b) False
Answer: a
Clarification: None.

8. What is Synonymy relation?
a) A is part of B
b) A denotes same as B
c) A is a kind of B
d) A is superordinate of B
Answer: b
Clarification: None.

9. What is Antonymy relation?
a) A is part of B
b) B has A as a part of itself
c) A denotes opposite of B
d) A is superordinate of B
Answer: c
Clarification: None.

10. Most semantic networks are not cognitive based.
a) True
b) False
Answer: b
Clarification: None.