Soft Computing Multiple Choice Questions
Soft Computing Multiple Choice Questions
In this article, we will discuss the most commonly asked multiple-choice questions related to Soft Computing.
The main purpose of writing this article is to target competitive exams and interviews. Generally, Soft Computing involves the basics of Fuzzy Logic, Neural Networks, and Genetic Algorithms. Here, we will try to cover all the frequently asked Soft Computing questions with the correct choice of answer among various options.
1) Which of the following is associated with fuzzy logic?
Crisp set logic
Many-valued logic
Two-valued logic
Binary set logic
Answer: b) Many-valued logic
Explanation: Since fuzzy logic can define the set membership with some specific value, it may have multiple set values.
2) The truth values of traditional set theory can be defined as _________ and that of fuzzy logic is termed as _________.
Either 0 or 1, either 0 or 1.
Between 0 & 1, either 0 or 1.
Either 0 or 1, between 0 & 1.
Between 0 & 1, between 0 & 1.
Answer: c) Either 0 or 1, between 0 & 1.
Explanation: A crisp set is usually defined by crisp boundaries containing the precise location of the set boundaries.
However, a fuzzy set is defined by the indeterminate boundaries containing uncertainty about the set's boundaries.
3) A Fuzzy logic is an extension to the Crisp set, which handles the Partial Truth.
True
False
Answer: a) True.
Explanation: None.
4) How many types of random variables are there in Fuzzy logic?
2
4
1
3
Answer: d) 3
Explanation: There are three types of random variables, i.e., Boolean, discrete, and continuous variables.
5) Which of the following represents the values of set membership?
Degree of truth
Probabilities
Discrete set
Both a & b
Answer: b) Degree of truth
Explanation: Both probabilities and degree of truth range between 0 and 1.
6) The probability density function is represented by
Continuous variable
Discrete variable
Probability distributions for Continuous variables
Probability distributions
Answer: c) Probability distributions for Continuous variables
Explanation: None.
7) _________is used for probability theory sentences.
Logic
Extension of propositional logic
Conditional logic
None of the above
Answer: b) Extension of propositional logic
Explanation: The version of probability theory makes use of an extension of propositional logic for its sentences.
8) Which of the following fuzzy operators are utilized in fuzzy set theory?
AND
OR
NOT
EX-OR
Answer: a), b) and c)
Explanation: In fuzzy logic, the AND, OR, and NOT operators represent the minimum, maximum, and complement.
9) What is the name of the operator in fuzzy set theory, which is found to be linguistic in nature?
Lingual Variable
Fuzz Variable
Hedges
None of the above
Answer: c) Hedges
Explanation: None.
10) Where can we use the Bayes rule?
To increase the complexity.
To decrease the complexity.
To solve queries
To answer the probabilistic query
Answer: d) To answer the probabilistic query
Explanation: Based on the given evidence, the Bayes rule can be utilized to answer the probabilistic queries.
11) Which of the following is offered by the Bayesian network?
Partial description of the domain
A complete description of the domain
A complete description of the problem
None of the above
Answer: b) Complete description of the domain
Explanation: A Bayesian network refers to a probabilistic graphical model, which epitomizes a set of variables and its corresponding dependencies thru a directed acyclic graph (DAG).
12) _________ represents the fuzzy logic
IF-THEN rules
IF-THEN-ELSE rules
Both a & b
None of the above
Answer: a) IF-THEN rules
Explanation: In fuzzy set theory, the fuzzy operators are defined on the fuzzy sets. When the fuzzy operators are anonymous, the fuzzy logic utilizes the IF-THEN rules.
In general, rules are expressed as:
IF variable IS property THEN action
13) Uncertainty can be represented by _________
Entropy
Fuzzy logic
Probability
All of the above
Answer: d) All of the above
Explanation: Entropy is the amount of uncertainty involved in data, which is represented by H(data).
14) Name the algorithms that acquire from complex environments to generalize, approximate and simplify solution logic.
Ecorithms
Fuzzy set
Fuzzy Relational DB
None of the above
Answer: b) Fuzzy set
Explanation: Rather than being associated with exponential growth, local structures are generally linked with linear growth in terms of complexity.
15) Which of the following condition can directly influence a variable by all the others?
Fully connected
Local connected
Partially connected
None of the above
Answer: a) Fully Connected
Explanation: None.
16) A perceptron can be defined as _________
A double layer auto-associative neural network
A neural network with feedback
An auto-associative neural network
A single layer feed-forward neural network with pre-processing
Answer: d) A single layer feed-forward neural network with pre-processing
Explanation: A perceptron is a single-layer neural network that consists of input values, weights, bias, net sum followed by an activation function.
17) What is meant by an auto-associative neural network?
A neural network including feedback
A neural network containing no loops
A neural network having a single loop
A single layer feed-forward neural network containing feedback
Answer: a) A neural network including feedback
Explanation: Auto associative networks are yet another kind of feed-forward nets trained to estimate the identity matrix in between network inputs and outputs by incorporating backpropagation.
18) Which of the following is correct?
I. In contrast to conventional computers, neural networks have much higher computational rates.
II. Neural networks learn by example.
III. Neural networks mimic the same way as that of the human brain
All of the above
(ii) and (iii) are true
(i), (ii) and (iii) are true
None of the above
Answer: a) All of the above
Explanation: Neural networks can run multiple operations in parallel, which is why they have higher computational rates than conventional computers. Neural nets mimic the working of the human brain. The idea behind neural nets is not to be programmed but to learn by examples.
19) Which of the following is correct for the neural network?
I. The training time is dependent on the size of the network
II. Neural networks can be simulated on the conventional computers
III. Artificial neurons are identical in operation to a biological one
All of the above
(ii) is true
(i) and (ii) are true
None of the above
Answer: c) (i) and (ii) are true
Explanation: The training time depends on the network size; the more the number of neurons, the more would be the possible states. Neural networks can be simulated on a conventional computer, but neural networks' main advantage - parallel execution - is lost. Artificial neurons are not identical in operation to biological ones.
20) What are the advantages of neural networks over conventional computers?
I. Neural networks learn from examples
II. They are more fault-tolerant
III. They are well suited for real-time operation due to their high computational rates
(i) and (ii) are correct
(i) and (iii) are correct
Only (i)
All of the above
Answer: d) All of the above
Explanation: Since neural networks learn by example, they are more fault-tolerant than conventional computers because they always respond, and small changes in the input do not hamper the output. Neural networks encompass parallel architecture, so it is pretty easy to achieve high computational rates.
21) Backpropagation can be defined as _________
It is another name given to the curvy function in the perceptron.
It is the transmission of errors back through the network to adjust the inputs.
It is the transmission of error back through the network to allow weights to be adjusted so that the network can learn.
None of the above
Answer: c) It is the transmission of error back through the network to allow weights to be adjusted so that the network can learn.
Explanation: Backpropagation is an efficient approach used to compute loss function's stress with respect to the parameters of neural networks. In order to minimize the loss function, backpropagation is mainly used to tune the weights of deep neural networks.
22) Which of the following is not the promise of an artificial neural network?
It can survive the failure of some nodes
It can handle noise
It can explain the result
It has inherent parallelism
Answer: c) It can explain the result
Explanation: The artificial neural networks fail to explain the results.
23) Having multiple perceptrons can solve the XOR problem satisfactorily because each perceptron can partition off a linear part of the space itself, and they can then combine their results.
True - This works always, and these multiple perceptrons learn to classify even complex problems.
False - Perceptrons are mathematically incapable of solving linearly inseparable functions, no matter what you do
True - Perceptron can do this but are unable to learn to do it - they have to be explicitly hand-coded
False - Just having a single perceptron is enough
Answer: c) True - Perceptron can do this but are unable to learn to do it - they have to be explicitly hand-coded
Explanation: None
24) Based on _________ membership function can be used to solve empirical problems.
Knowledge
Learning
Examples
Experience
Answer: d) Experience
Explanation: The membership function of a fuzzy set is a generalization of the indicator function for classical sets.
25) A 3-input neuron is trained to output a 0 when the input is 110 and a 1 when the input is 111. After generalization, the output will be 0, when and only when the input is:
000 or 110 or 011 or 101
000 or 010 or 110 or 100
100 or 111 or 101 or 001
010 or 100 or 110 or 101
Answer: b) 000 or 010 or 110 or 100
Explanation: Before generalization, the truth table is as follows:
Here, $ represents the don't know cases, and the output is random.
After generalization, the truth table will be:
26) 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:
76
238
123
119
Answer: b) 238
Explanation: In order to find out the output, we multiply the weights with their respective inputs, add the results and then further multiply them with their transfer function.
Thus, output= 2*(1*4 + 2*10 + 3*5 + 4*20) = 238
27) A neuro software can be defined as:
A powerful and easy neural network
A software that is used to analyze neurons
Software utilized by a neurosurgeon
A software aimed to assist experts in the real world
Answer: a) A powerful and easy neural network
Explanation: None.
28) What is the name of the network, which includes backward links from the output to the inputs as well as the hidden layers?
Perceptron
Self-organizing maps
Multi-layered perceptron
Recurrent neural network
Answer: d) Recurrent Neural Network
Explanation: A recurrent neural network is yet another kind of artificial neural network, where the output derived from the previous step is fed as an input to the current step.
29) Which of the following is true for unsupervised learning?
Some specific output values are disclosed
Some specific output values aren't disclosed
No relevant inputs value is specified
Both inputs as well outputs are specified
Neither inputs nor outputs are given
Answer: b) Some specific output values aren't disclosed
Explanation:
In unsupervised learning, the model learns itself from the data without having a predicted result. Either the data is not given with a target response variable (label), or none chooses to label a response. In general, it is mainly treated as a pre-processing step for supervised learning models.
Here, the goal is to determine the patterns, deep insights, understand variation, find unknown subgroups (amongst the variables or observations), and so on in the data.
30) What is involved in inductive learning?
Inconsistent Hypothesis
Consistent Hypothesis
Estimated Hypothesis
Irregular Hypothesis
Regular Hypothesis
Answer: b) Consistent Hypothesis
Explanation: Inductive learning is used to find a consistent hypothesis, which agrees with the examples. The difficulty of the task relies on the chosen representation.
31) Which of the following statement is correct?
Not all formal languages are context-free
All formal languages are context-free
All formal languages are like natural language
Natural languages are context-oriented free
Natural language is normal
Answer: a) Not all formal languages are context-free
Explanation: Not all formal languages are context-free.
32) Which of the following is incorrect?
The union and intersection of two context-free languages are context-free.
The reverse of context-free language is context-free, but its complement does not need to be.
Every regular language is context-free as it can be easily explained by regular grammar.
The intersection of a context-free language and a regular language is always context-free.
The intersection of two context-free languages is context-free.
Answer: e) The intersection of two context-free languages is context-free.
Explanation: The union and concatenation of two context-free languages are always context-free, but the intersection need not be context-free.
33) Automated vehicle is an application of _________
Unsupervised learning
Supervised learning
Reinforcement learning
Active learning
Answer: b) Supervised learning
Explanation: In an automatic vehicle, a set of input visions and corresponding actions are available for learners, so it can be concluded that it is an example of supervised learning.
34) _________ is not counted in different learning method.
Analogy
Memorization
Introduction
Deduction
Answer: c) Introduction
Explanation: Analogy, memorization, and deduction are involved in different learning methods.
35) Which of the following models are utilized for learning?
Neural networks
Decision trees
Propositional and FOL rules
All of the above
Answer: d) All of the above
Explanation: Neural networks, Decision trees, Propositional and FOL rules are altogether utilized as a learning model.
36) Which of the following is the correct example of active learning?
Dust Cleaning Machine
News Recommender System
Automated Vehicle
None of the above
Answer: b) News Recommender System
Explanation: Active learning is such a kind of learning, which involves the teachers. It enables the learner to ask relevant examples related to perception-action pairs that will further augment the performance.
37) Which of the following is termed exploratory learning?
Active learning
Supervised learning
Reinforcement learning
Unsupervised learning
Answer: d) Unsupervised learning
Explanation: Exploratory learning can be defined as a teaching and learning approach that encourages the learner to study and scrutinize new material, regardless of being dependent on any supervision.
38) _________ helps in modifying the performance element, assisting in making a better decision.
Learning element
Performance element
Changing element
None of the above
Answer: a) Learning element
Explanation: Learning elements assist in making a better decision by modifying the performance element.
39) Which of the following is considered while determining the nature of the learning problem?
Problem
Feedback
Environment
All of the above
Answer: b) Feedback
Explanation: The feedback is utilized to determine the nature of the learning problem faced by the agent.
40) Which of the following is chosen among the multiple consistent hypotheses?
Ockham razor
Learning element
Razor
None of the above
Answer: a) Ockham razor
Explanation: Ockham razor prefers the simplest hypothesis consistent with the data intuitively.
41) Which of the following takes input as an object described by a set of attributes?
Graph
Decision graph
Tree
Decision tree
Answer: d) Decision tree
Explanation: The decision tree takes input as an object described by a set of attributes followed by returning a decision.
42) A neural network can answer
For Loop questions
What-if questions
If-The-Else Analysis questions
None of the above
Answer: b) What-if questions
Explanation: None
43) Feature of ANN in which ANN creates its own organization of representation of information it receives during learning time is
Adaptive Learning
What-if analysis
Self-Organization
Supervised learning
Answer: c) Self-Organization
Explanation: The term self-organization refers to how people unify their common behavior to form global order by interacting among themselves instead of interacting through external intervention and instruction.
44) In artificial neural network, interconnected processing elements are termed as _________
Weights
Nodes or neurons
Axon
Soma
Answer: b) Nodes or neurons
Explanation: A neural network comprises several simple, highly interconnected processing elements that process data by its dynamic state response to external elements.
45) Each connection link in ANN is linked with ________ that contains statics about the input signal.
Neurons
Activation function
Weights
Bias
Answer: c) Weights
Explanation: Weights in artificial neural networks play an efficient role as they are responsible for transmuting the input data within the network's hidden layers.
46) Artificial neurons are capable enough to model original neurons networks similarly as they are found in the human brain
True
False
Answer: a) True
Explanation: None.
47) Name the input function received by neurons, which is also known as the neuron's internal state.
Weight
Bias
Activation or neuron's activity level
None of the above
Answer: c) Activation or neuron's activity level
Explanation: None.
48) What is the name of the process that represents modified elements of the DNA?
Selection
Mutation
Recombination
None of the above
Answer: b) Mutation
Explanation: Mutation can be defined as a change in the DNA that is responsible for bringing about benefits, harm, or nothing.
49) Which of the following is the best representation of individual genes?
Coding
Conversion
Encoding
None of the above
Answer: c) Encoding
Explanation: Encoding is a process of transmuting phenotype space to genotype space.
50) What is the name of the operator that is functioned on the population?
Recombination
Reproduction
Mutation
None of the above
Answer: b) Reproduction
Explanation: A genetic algorithm initializes the population by utilizing random values followed by running each individual from the population through the fitness function. Then the fittest one gets selected among the population to reproduce by using the reproduction function. The process of evaluation and reproduction is repeated until a desired number of iterations have been passed.
51) Name the selection method that is found to be less noisy.
Boltzmann solution
Remainder solution
Stochastic remainder solution
None of the above
Answer: c) Stochastic Remainder Solution
Explanation: None.
52) In how many steps does a crossover operator proceed?
2
3
4
5
Answer: b) 3
Explanation: In a genetic algorithm, the crossover can be entitled recombination, which is nothing but a genetic operator that associates the genetic information of two parents to produce a new offspring.
53) Which of the following best relate to reinforcement learning?
Error based learning
Backpropagation learning
Output-based learning
None of the above
Answer: c) Output based learning
Explanation: Reinforcement learning is another branch of machine learning that learns from the output errors and improves them in the subsequent iterations.
54) ________ helps in converting a given bit pattern into another bit pattern by using logical bit-wise operation.
Masking
Segregation
Conversion
Inversion
Answer: a) Masking
Explanation: None
55) The ________ causes all the bits in the first operand to shift to the left by the number of positions indicated by the second operand.
Shift right
Shift left
Shift operator
None of the above
Answer: b) Shift left
Explanation: None
56) Which of the following is not a specified method used for selecting the parents?
Tournament Selection
Steady-state
Elitism
Boltzmann selection
Answer: b) Steady-state
Explanation: None.
57) ________ deals with uncertainty problems with its own merits and demerits
Neuro-fuzzy
Neuro-genetic
Fuzzy-genetic
None
Answer: a) Neuro-fuzzy
Explanation: Neuro-fuzzy refers to the amalgamation of neural networks and fuzzy logic in the field of artificial intelligence. It is nothing but a fuzzy system whose parameters learn through the learning algorithms acquired from the neural networks.
58) What does FAM stand for?
Fuzzy Association Memory
Fuzzy Associative Memory
Fuzzy Assist Memory
None of the above
Answer: b) Fuzzy Associative Memory
Explanation: Fuzzy associative memory is a kind of neural network that stores the associations of patterns. It recalls the stored patterns from the noisy inputs.
59) Which of the following exhibits non-linear functions to any desired degree of accuracy?
Neuro-fuzzy
Neuro-genetic
Fuzzy-genetic
None of the above
Answer: c) Fuzzy-genetic
Explanation: Fuzzy-genetic can be identified as a system built with the help of genetic algorithms, assisting in imitating the process of natural evolution, which is necessary for identifying its parameter and structures.
60) Matrix crossover is also known as _________
One dimensional
Two dimensional
Three dimensional
None of the above
Answer: b) Two dimensional
Explanation: Matrix crossover initially selects three parents. Then each bit of the first parent is associated with that of the second parent. If both are found to be similar, then the bit is taken for the offspring, else the third parent's bit is considered for the offspring.
Comments
Post a Comment