We Offer 100% Job Guarantee Courses (Any Degree / Diploma Candidates / Year GAP / Non-IT / Any Passed Outs). Placement Records
Hire Talent (HR):+91-9707 240 250

Interview Questions

Artificial Intelligence Interview Questions and Answers

Artificial Intelligence Interview Questions and Answers

Artificial Intelligence Interview Questions and Answers

Artificial Intelligence Interview Questions and Answers for beginners and experts. List of frequently asked Artificial Intelligence  Interview Questions with answers by Besant Technologies. We hope these Artificial Intelligence  interview questions and answers are useful and will help you to get the best job in the networking industry. This Artificial Intelligence  interview questions and answers are prepared by Artificial Intelligence Professionals based on MNC Companies expectation. Stay tuned we will update New Artificial Intelligence  Interview questions with Answers Frequently. If you want to learn Practical Artificial Intelligence  Training then please go through this Artificial Intelligence Training in Chennai and Artificial Intelligence Training in Bangalore

Best Artificial Intelligence Interview Questions and Answers

Besant Technologies supports the students by providing Artificial Intelligence  interview questions and answers for the job placements and job purposes. Artificial Intelligence  is the leading important course in the present situation because more job openings and the high salary pay for this Artificial Intelligence  and more related jobs. We provide the Artificial Intelligence online training also for all students around the world through the Gangboard medium. These are top Artificial Intelligence  interview questions and answers, prepared by our institute experienced trainers.

Artificial Intelligence  interview questions and answers for the job placements

Here is the list of most frequently asked Artificial Intelligence  Interview Questions and Answers in technical interviews. These questions and answers are suitable for both freshers and experienced professionals at any level. The questions are for intermediate to somewhat advanced Artificial Intelligence professionals, but even if you are just a beginner or fresher you should be able to understand the answers and explanations here we give

1). Write a python program for drawing a flower shown below
>>import turtle
>>bob = turtle.Turtle()
>>def arc(t,r,angle):
>>    circumference = 2*3.14*r
>>    arc_length = circumference * (angle/360)
>>    n = 50
>>    for i in range(100):
>>       print(bob.fd(arc_length/n))
>>       print(bob.lt(angle/n))
>>def petal(t,r,angle):
>>    for i in range(2):
>>       arc(bob,100,60)
>>       bob.lt(180-angle)
>>def flower(t,n,r,angle):
>>    for i in range(n):
>>       petal(t,r,angle)
>>       bob.lt(360/n)
2). Write a python program which should satisfy the following diagram:
>>import turtle
>>bob = turtle.Turtle()
>>def circle(t,r,angle):
>>   circumference = 2*3.14*r
>>   arc_length = circumference * (angle/360)
>>   n = 50
>>   for i in range(490):
>>      print(bob.fd(arc_length/n))
>>      print(bob.lt(angle/n))
>>def square(t,length):
>>    print(bob.lt(45),length)
>>    print(bob.fd(145),length)
>>    print(bob.lt(90),length)
>>    print(bob.fd(140),length)
>>    print(bob.lt(90),length)
>>    print(bob.fd(145),length)
>>    print(bob.lt(90),length)
>>    print(bob.fd(140),length)
3). In a family of four members, the father earns 30,000 and the mother earns 20,000 salary to live a life. The son earns 16,000 and the daughter earns 10,000. If all are going for a shopping to buy the following list of items for each one’s interest then compare the expenditure and income for each person by writing a python program.
  • Chudithar – 5,000 For Daughter
  • Make-up-kit – 10,000 For Daughter
  • Movie ticket – 1500 For All
  • Shirt & Jean – 1000For Son
  • Saree – 6,000 For Mother
  • Groceries – 4,000 For Mother
  • Traveling Expense – 10,000 For All
  • Food & Beverages – 3,000 For All
>>Father = 30000
>>Mother = 20000
>>Son = 16000
>>Daughter = 10000
>>Total = Father + Mother + Son + Daughter
>>Daughter_expenditure = 15000
>>Son_expenditure = 1000
>>Mother_expenditure = 10000
>>Combined_expenditure = 14500
>>if Daughter_expenditure > Daughter:
>>    exp = Daughter_expenditure + Daughter
>>    Dexp = exp – Daughter
>>    print(“Daughter expenditure %d”, Dexp)
>>    Dexp = Daughter – Daughter_expenditure
>>    print(“Daughter expenditure %d”, Dexp)
>>if Son_expenditure > Son:
>>    exp = Son_expenditure + Son
>>    Sexp = exp – Son
>>    print(“Son expenditure %d”, Sexp)
>>    Sexp = Son – Son_expenditure
>>    print(“Son expenditure %d”, Sexp)
>>if Mother_expenditure > Mother:
>>    exp = Mother_expenditure + Mother
>>    Mexp = exp – Mother
>>    print(“Mother expenditure %d”, Mexp)
>>    Mexp = Mother – Mother_expenditure
>>     print(“Mother expenditure %d”, Mexp)
>>if Combined_expenditure > Total:
>>     Texp = Combined_expenditure + Total
>>     print(“Combined expenditure %d”, Texp)
>>     Texp = Total – Combined_expenditure
>>     print(“Combined expenditure %d”, Texp)
4). Debug the code: >>print(‘Our good friend print’) >>print = 77. If you see here, the reserved word is used as a variable. Whether the statement print = 77 is correct? If it is correct, justify the reason.

Print = 77 is correct. The python interpreter allows the print statement to be used as a variable also, but once it is assigned a value and recognized as a variable then it is not recognized as a reserved word in the following statement.

5). X is the input layer which contains the numbers from 0-9 and b is the bias. W is the weight and Y is the output of the network in which the number 8 when given as input will come as “eight” in words.
  1. Mention what type of library function is used for classification technique and why?
  2. Explain the training methodology.

A) Scikit – learn is used for classification technique in the above neural network because the sci-kit – learn is the best library for classifying a limited set of data.

B)The training methodology is as follows:

  • Loading the dataset
  • Accessing the target and distribution values
  • Splitting the data into training and testing set
  • Clustering the data
  • Evaluation of the model.

Debug the code:  >>import tensorflow as tf

>>hello = tf.constant(‘Hello,TensorFlow!’)

>>sess = tf.session()


7). What is wrong in the above code?

The line sess = tf.session() is wrong and the correct line is sess = tf.Session() because the python is case sensitive and therefore there is a syntax error in this code.

8). What is the system bit that is required to install tensorflow on windows and why?

64 bit is the minimum system bit requirement for installing tensorflow as they are not available for other types of system bit in windows.

9). Why is convolutional neural network prescribed for image processing rather than other types of neural networks?

The convolutional neural network is prescribed than other types of neural network for image processing because of the capability to enhance the multi-layered perceptron (MLP) by inserting the convolutional layers. This helps in training the network on a pixel – by – pixel layer.

10). What is the difference between Machine learning and Artificial Intelligence?
Machine Learning Artificial Intelligence
The machine learning is a subset of AI. The artificial intelligence is a mimic of human intelligence that can be done through machine learning.
All machine learning belongs to AI. All AI does not belong to machine learning.
11). What are the two different categories of a Deep learning AMI?

The two different categories of a deep learning AMI are Conda AMI and Base AMI.

12). What happens when we terminate the instance in AWS account?

When we terminate the instance in AWS then we will be no longer able to use the particular instance and we need to create a new instance for performing any operation.

13). What are the libraries that are already available in a deep learning AMI?

The following are the list of libraries already available:

  • MxNet
  • TensorFlow
  • Keras with TensorFlow as default backend
  • Keras with MxNet as default backend
  • Caffee
  • CNTK
  • Theano
  • PyTorch
  • NVidia
  • CUDA
  • CuDNN


14).How to get connected to the Amazon server using putty?

Open the putty terminal

  1. Give the hostname as “ubuntu@PublicDNS” if you are using ubuntu server give as ubuntu and if in the place of PublicDNS give the statement shown while running the instance.
  2. Assign the port number as 22.
  3. Click the Auth column given in the left side of the putty below SSH.
  4. Click the browse button given on the right. Select the private key file for your instance that is with the .ppk extension.
  5. Click the open button given below and now a new pop up window opens which says whether you trust the host. Click yes then now the server gets opened.
15). What is the use of MxNet?

The MxNet is useful for easy programming flexibility, portability and scalability. The MxNet supports multiple languages like C++, Python, R, Julia, Perl, etc. Therefore, it eliminates the need to learn a new language. It has faster training capabilities.

16). How to find the boundary line for classifying two objects in a neural network?

In general, the boundary line for classifying any two objects is done by finding the equation y=mx+c where y is the output, x is the input, m is the slope and c is the constant.

17). Describe about Classical AI & Weak AI?

Classical AI:

It has more concerned with deductive thought as provided with set of constraints, deduce a conclusion

Weak AI:

It simply predicts that some features that are resembling to the human machine intelligence can be incorporated to computer make it more useful tools in it.

18). What is a production rule consist of and the which search method take a less memory?

Production Rule:

It is a rule which comprises of a set of rule and a sequence of steps in it.

Search Method:

Depth First Search is the method that would takes the less memory for any of the process to follow.

19). How A* algorithm is works with search method?

A* Algorithm Search Methodology: A* algo’s is fully based on first search method and it provides an idea of optimization and quick choose of the path and along-with all the characterisitics lies on it the same.

20). What is Heruistic Function & How Neural Networks working in AI?

Heuristic Function:

It is an alternatives function for ranks in search algorithms and at each branching step based on the available information to decide which branch that needs to be follow.

Neural Networks In AI:

In general it is an biological term, but in artificial intelligence it is an emulation of a biological neural system, which receives the data, process the data and gives output based on the algorithm and empirical data.

21). How the Strong AI & Statistical AI works?
  • Strong AI:
    • It claims that the computer can be made to think on a level equal to humans. This is what the strong ai performs.
  • Statistical AI:
    • It has more concerned with inductive thought as provided with set of patterns, induce with the trend.
22). How to resolve a problem with the Game Playing Problem Methodology?

Game Playing Problem Methodology:

Heuristic Approach is the best way to proceed further for game playing problem, though it will use the technique based on intelligent guesswork. Let us say an example like chess game – Chess between human and computer as it will proceed with brute force computation and looking at hundreds of thousands of positions.

23). Simple Explanation about Alternate, Artificial, Compound and Natural Key?
  • Natural Key:
    • It is one of the data element that is stored within a construct, and it is optimized as the primary key.
  • Compound & Artifical Key:
    • If there is no single data element that uniquely defines the occurrences within a construct, then integrating multiple elements to create a unique identifier for the construct and it is called as compound key.
    • If there is no obvious key either stands alone or compound is available, then the last report is to simply create a key by assigning a number to each record or occurrence and it is called a artificial key.
24). What is an Agent and How Partial Order or Planning Involve?
  • Agent:
    • Like, anything that preceives its environment by the sensors, and act upon an environment by effectors are called as Agent. (e.g. Robots, Programs, Humans, HCI, HMI etc.)
  • Partial Order or Planning:
    • Instead of searching over possible situation that involves searching over the space of possbile plans. Then the idea can be construct as a plan piece by piece.
25). On How many ways we can construct a plan and which property is considered as not a desirable property of a logical rule-based system?

Ways to Construct a Plan:

  • Action, nothing but add an operator
  • Secondly, add an ordering constraints between the operators Property not desirable:
  • Attachment is the one which not considered as a logical-rule based system in artificial intelligence.
26). How the Generality and Top-Down Parser works?
  • Generality:
    • It is the ease measure with which the method can be adapted to different domains of application
  • Top-Down Parser:
    • It begins by hypothesizing a sentence and successively predicting lower level constituents until that the individual pre-terminal symbols are written.
27). How FOPL works in AI?
  • FOLP:
    • It’s nothing but a first order predicate logic we called as shortly FOPL.
  • Working Methodology:
    • It needs a language to express assertions about certain world
    • It needs an inteference system to deductive apparatus whereby we may draw conclusions from such assertions
    • It needs a semantic based on set theory
28). How AI perform against Frames and Scripts?
  • Frames:
    • They are variant of semantic networks which is one of the popular ways of presenting non-procedural knowledge in an expert system.
    • A frame which is an artificial data structure is used to divide the knowledge into substructure by representing in stereotyped-situations.
  •  Scripts:
    • It is similar with respect to frames but except the values that fill the slots must be ordered.
    • Though, scripts used in natural language understanding systems to organize a knowledge base in terms of the situation that the system should understand.
29). Describe the Building Mehtodology of Bayesian Network and Bayes Model with resepect to AI?
  • Build Methodology of Bayesian Network:
    • The Bayesian Network creation, falls under the consequence between a node and its predecessors.
    • And also the node can be conditionally independent of its predecessors.
  • Build Methodology of Bayes Model:
    • There are three terminology that required to build a Bayes Model.
    • And they should be one conditional probability based and the other two unconditional probability based.
30). Breif the Literal that help for top-down inductive learning methods?

The below are the few literal that currently used for inductive learning methodology:

  • Predicates
  • Equality & In-Equality
  • Arithmetic Literals
31). What is Hidden Markov Model & Signal Flow In Speech Recoginition?
  •    HMM:
    • It is ubiquitous tool for modelling time series data or to model sequence behaviour of the system.
    • It can be used in almost all the current speech based systems.
    • It can be stated in single discrete random variable.
  •   Signal Flow Used:
    • Acoustic signal flow is the one which can be used in the speech to identify the sequence of words.
32). Which is the similar operation performed by the drop-out in neural network?

Ans. Bagging; Dropout can be seen as bagging, it each training step it creates a different network which is trained with backpropagation. It is same as ensemble of many networks trained with a single sample.

33) . How a neural networks became a universal function approximators?

Ans. Because of the Activation Functions; Yes, the activation functions are helpful in making the functions piecewise linear which in turn helps in representing the any complex function.

34) . What are the possible reasons for slow learning rate in the Neural networks?
  1. Low learning rate
  2. High regularization
  3. Stuck at local Minima

Low learning rate : Because of this the minima is very slow by gradient descent algorithm

High regularization : This will bound the parameter values to the very low values and complexity is very much decreased

Stuck at local Minima : When it is stuck at local minima it requires more iterations or change in learning rate to get out of it.

35). Comment on batch Normalization?

Ans. To make the data standardized before sending it to the another layer. It reduces the impacts of previous layers by keeping the mean and variance constant, makes the layers independent of each other. The convergence becomes faster.

36). What are the different NLP tasks deep learning can be applied?

Ans. Machine translation, Sentiment Analysis, Question and Answer system

Machine translation : Sequence to sequence models are used for this.

Sentiment Analysis : Classification techniques on text using neural networks

Question and Answer system : This is again a Seq to seq model

37). What are the disadvantages of representing the words with one hot vectors?

Ans. 1. No similarities are captures, 2. Very high no. of dimensions to compute One hot vectors are very sparse vectors which are orthogonal to each other and each vector is represented by the same number of total number of different words in corpus. So it is high dimensional as well as no similarities are captured.

38). Simple explanation of one hot representation to lower dimension conversion?

Ans. Trained Neural Network with one hidden layer gives the lookup table. First of all train a model NN model with one hidden layer to predict the context words, after the training the actual weight matrix that is learnt by hidden layer is user for representing the words.

39). How dropout is different from regularization related?

Ans. When dropout rate is very high, regularization will be very low. It constrains adapting network to the data to avoid overfitting.

40). How BPTT varies from vanilla backpropagation?

Ans. In BPTT, in each time step, for each weight the gradients are summed together. Errors will be calculated for each timestep. The weights are updated after the network is rolled back.

41). What is the way of dealing with “Exploding Gradient” problem in RNNs?

Ans. Gradient clipping, gradient is set to the threshold. Gradient clipping will chop the gradients or restricts them to a Threshold value to prevent the gradients from getting too large.

42). What is advantage of pooling layer in convolutional neural networks?

Ans. Statistical Average of the Output of the convolution layer, which is easy to compute on the further steps. This reduces the spatial size of the representation to reduce the amount of parameters and computation in the network. Pooling layer operates on each feature map independently.

43). Can RNN be unfolded into full CNN with infinite length?

Ans. TRUE, RNN’s neuron can be thought of as a neuron sequence of infinite length of time steps.

44). Which of the following data augmentation technique would you prefer for an object recognition problem?

Ans. Horizontal flipping, Rescaling, Zooming; Deep learning model actually require so much of data to train the models. It is very data hungry. And to take advantage of training the models with various angles of objects we go with this data augmentation technique.

45). Size of Convolution kernel would necessarily increase the performance of CNN?

Ans. FALSE, it is hyperparameter so changing it we can increase or decrease performance. We initially randomly initialize the weights for these kernels and they learn the correct weight by back propagation. So it make more computation time and occupy resources.

46). Why do we prefer LSTM over RNN?

Ans. Due to vanishing gradient, Vanishing gradient problem depends on the choice of the activation function. Activation functions (e.g sigmoid or tanh) usually ‘squash’ input into a very small number range in a very non-linear fashion.

47). What are techniques can be used for the keyword normalization?

Ans. Stemming and Lemmatization.

Stemming usually is the process that cuts off the ends of words in the hope of deriving the root word most of the time. So in simple word it just removes the affixes.

Lemmatization uses vocabulary and morphological analysis of words, and most of the time root it to the correct root words, ex: good for best. The root words are called as lemma.

48). Features used for accuracy improvement of in NLP classification model?

Ans. Frequency counts, Vector Notation, POS, Dependency grammar

49). What is the major difference between CRF (Conditional Random Field) and HMM (Hidden Markov Model)?

Ans. HMMs are generative models , models the joint distribution P(y,x). Therefore, model the distribution of the data P(x). These computations might take longer time compared to directly computing the conditional probability.

CRFs are discriminative models which model conditional probability P(y|x). As such, they do not require P(x) to be modelled. This results in faster performance, as they need fewer parameters to be learned.

50). What is generally the sequence followed when building a neural network architecture for semantic segmentation for image?

Ans. Encoder network on input and Decoder network on output.

The encoder is a classification network which is pre trained and just like VGG/ResNet and followed by a decoder network.

The decoder is to project the lower resolution features learnt by encoder onto higher resolution space to get the dense classification.

51). Can Normal Neural Network has long term dependencies on the Sentences?

Ans. NO, RNNs and LSTMs can have them. This is because the hidden state information is also passed to the consecutive layers in RNN and LSTM.

52). How the new states can be generated in genetic algorithm. Choose option?

a) Composition
b) Mutation
c) Cross-over
d) Both Mutation & Cross-over


Answer: d
Explanation: New states are generated by mutation and by crossover, which combines a pair of states from the population.

53). What is the main focus area of artificial intelligence?

a) To solve real-world problems
b) To solve artificial problems
c) To explain various sorts of intelligence
d) To extract scientific causes


Answer: c

54). The most primary method that people use to sense their surrounding is:

a) reading
b) writing
c) speaking
d) seeing


Answer: d

55). Where Natural language understanding applications can be seen:

a) natural language interfaces
b) natural language front ends
c) text understanding systems
d) all of the mentioned


Answer: d

56). Which algorithm that are to some extent similar to backward chaining algorithm?

a) Depth-first search algorithm
b) Breadth-first search algorithm
c) Hill-climbing search algorithm
d) All of the mentioned” open=”no” style=”default” icon=”plus” anchor=”” class=””]


Answer: a
Explanation: It is depth-first search algorithm because its space requirements are linear in the size of the proof.

57). For building a bayes model, how many terms are required?

a) 1
b) 2
c) 3
d) 4″ open=”no” style=”default” icon=”plus” anchor=”” class=””]


Answer: c
Explanation: The three required terms are a conditional probability and two unconditional probability.

58). Which among the following specifies the prior probability of each utterance?

a) Sound model
b) Model
c) Language model
d) All of the mentioned” open=”no” style=”default” icon=”plus” anchor=”” class=””]

Answer: c
Explanation: Because it contains the group of words which can help to specify the prior probability of each utterance.

59). How can you evaluate 1.25 + sqrt (144) in LISP?

a) 1.25+sqrt (1.44)
b) (1.25+sqrt (1.44))
c) (+1.25 sqrt (1.44)
d) All of the mentioned” open=”no” style=”default” icon=”plus” anchor=”” class=””]

Answer: c

60). Answer True or False: Zero sum games are the one in which there are two agents whose actions is most alternate and in which the utility values at the end of the game are always the same.

a) True
b) False” open=”no” style=”default” icon=”plus” anchor=”” class=””]

Answer: b
Explanation: Utility values are always same and opposite.

61). How Branches are located in AI?


– Expert System

– Pattern Recognition

– Swarm Intelligence

– Data Mining

– Genetic Algorithm

– Neural Networks

– Statistical AI

– Fuzzy Logic

62). Describe Game Theory with AI Relation?

Game Theory:

– An AI System will use the game theory for the purpose of the requirement that enhance as the more than a participant. So, the relation between the game have two parts like,

  1.  Participant Design
  2.  Mechanism Design
63). How an AI can find Conference Information?

Conference Information:

– A webpage that let you search for upcoming or previous conference in AI disciplinary way which can maintained by a Georg Thimm. So, that we called as AI based Conference Information.

64). How Relational Knowledge used in AI?

Relational Knowledge:

– A knowledge representation scheme in which facts are represented as a set of relations. Let’s say e.g. Knowledge about a player can be represented using a relation called as player which consist of three fields,

  1. Player Name
  2. Height
  3. Weight
65). Describe the methodology of Inheritable Knowledge in AI?

Inheritable Knowledge:

– A knowledge repesentation scheme which can be represented in the form of objects, their attributes and the corresponding values of the attributes.

– The relation between the object defined using a isa property in it.

– Let’s say an e.g. In a game two entities like Amature Male & Person are presented as objects than the relation between the two is that Amature Male is a Person.

66). How NLP works against AI?


– Natural Language Processing shortly called as NLP.

– It’s nothing but an processing and prehaps based understanding.

– Like, process an computational linguistics with the help of read the scenario by natural human recognizable language.

67). Describe about Supervised Learning?

Supervised Learning:

– It is one of the machine learning process.

– It process against the output that fed back from computer for software to learn from for more accurate result in the next time.

– It can receive initial training to start from machine.

68). State the Unsupervised Learning?

Unsupervised Learning:

– Different Methodology of machine learning.

– Though, in contrast with unsupervised machine learning mean a computer will learn without training to base its learning on.

69). In Which Scenario AI Accomplished?

– In generic computing machinery & intelligence, computers would able to pass the tuning test at a reasonably sophiscated level, in a particular level.

– The average interrogator would not be able to identify the computer     correctly more than 70 per cent of the time after a minute of conversation.

70). How the Semantic Analysis used in AI?

Semantic Analysis:

– Semantic will helps to extract the meaning from the group of

sentence. So, that the semantic would be helpful in AI.

71). What is PERCEPTRON?

Ans. It is a single layer feed-forward neural network

72). Define backpropagation?

Ans. Error is transmitted back through the network to allow weights to be adjusted, using which system will learn

73). One of the primary purposes of using activation function is to find non-linear decision surface?

Ans. True, the main purpose of using the Activation function is to find non-linear decision surface.

74). If the number of input and output nodes are 8 and 2 respectively. What should be the number of nodes in the hidden layer according to geometric pyramid rule?

Ans. The number will be 4.

75). Is the output range of the sigmoid activation function is (0,1)?

Ans. True

76). Is the output range of tangent activation function is (-1,0)?

Ans. False

77). A multi-layer neural network can address the XOR problem?

Ans. True

78) Momentum is used to diminish the fluctuations in weight changes. Is the statement true or false?

Ans. True

79). Recurrent Neural Network can handle various length of the input sequence. Is the statement true or false?

Ans. True

80). Recurrent neural networks have different weights at different times. Is the statement true or false?

Ans. False

81). DL overcomes bias and variance by using large datasets, building small nets and using large regularizations. Is the statement true or false?

Ans. False

82). What information is to be thrown away from cell state?

Ans. Sigmoid Layer in forget gate.

83). How much information is to be added to cell state?

Ans. Sigmoid in the write gate.

84). How much of context has to be taken into the next state?

Ans. Sigmoid layer in the read gate.

85). Which of the following techniques can be used when more contexts are needed?

Ans. RNN can be used when more contexts are needed.

86). Problem: Image Recognition of a crack on the walls. Synthesized data: 1000000 images of cracks and non-cracked. Real Data: 10000 cracks captured in a real scenario. Which of the following is the best split?


SynthTraining: 950,000

SynthValid: 50,000

RealValid: 5000

RealTest: 5000

87). What is Activation function for a multi-category classification?

Ans. Softmax

88). If a linear programming problem has a solution at all, it will have a solution at some corner of the feasible region

Ans. True

89). The conditional probability exists when one event is dependent on another. Is the statement true or false?

Ans. True

90). For solving the integer programming problem using linear programming technique, we round-off the numeric solution? Is the statement true or false?

Ans. False

91). Every LP problem has a solution. Is the statement true or false?

Ans. False

92). In linear programming, what is objective function and constraints?

Ans. Linear

93). Give a valid objective function for a linear programming problem?

Ans. min {4x + 3y + (2/3) z}

94). When the problem involves the allocation of n different facilities to n different tasks, it is often termed as?

Ans. Assignment problem

95). Maximize Z = 3x + 4y. Subject to the constraints: x + y <= 4, x >= 0, y >= 0. What is the max value of Z?

Ans. 16

96). On what the number of constraints in dual depends on?

Ans. The number of constraints in dual depends on Number of decision variables in primal.

97). Name any one of the problem with Neural Networks with more layers.

Ans. Overfitting is a problem in Neural Networks.

98). Auto-encoders are a supervised learning algorithm. Is the statement true or false?

Ans. False

99). Which technique performs similar operations as a dropout in a neural network?

Ans. Bagging

100). In Deep Learning, back propagation uses which method?

Ans. In Deep Learning the backpropagation uses weights that are randomly generated.

101). Which of the following gives non-linearity to a neural network?

Ans. Rectified Linear Unit

102). What is a dead unit in a neural network?

Ans. A unit which doesn’t update during training by any of its neighbor.

103). Why Batch Normalization is helpful?

Ans. Batch normalization is helpful because it normalizes (changes) all the input before sending it to the next layer.

104). When we incorrectly reject a true null hypothesis Type, I error occurs. Is the statement true or false?

Ans. True

105). A Type II error occurs when we incorrectly fail to reject a false null hypothesis. Is the statement true or false?

Ans. True

106). Statistical power is the probability of rejecting the null when it is false. Is the statement true or false?

Ans. True

107). A normally distributed population has mean 16. Consider all samples of size 7 and standard deviation‘s’. The values of (mean(x) – 16)/ (s/sqrt(7)) are distributed as?

Ans. It is a distribution with degree of freedom = 6.

108). The t-distributions are skewed or symmetrical.

Ans. Symmetrical

109). A random sample of size n = 25 is drawn from a population with mu = 50 and sigma = 10. If the mean of the sample is 45, what is sampling distribution mean of the sample mean?

Ans. 50

110). T-distribution has a variance: can be less than or greater than one or always greater than one?

Ans. It is always greater than one.

111). At 90% confidence level, what is the probability of type-I error?

Ans. 0.1

112). What is the X2 test for independence?

Ans. Right tailed

113). An ANOVA is applied to data obtained from 6 samples where each sample contains 20 observations. What are Degrees of freedom for the critical value of F?

Ans. 5 numerator and 114 denominator degrees of freedom.

114). Continuity correction for x <= 7 would be.

Ans. x < 7.5

115). For Independent observations X and Y, Var(X-Y) =……?

Ans. Var(X) + Var(Y)

116). The correct set of definitions for the following symbols: μ σ x ¯s is.

Ans. Population mean, population standard deviation, sample mean, sample standard deviation.

117). The presence of an outlier has more impact on the median than the mean. Is the statement true or false?

Ans. False

118). What is the use of Q-Q plot?

Ans. To check the normality of the errors.

119). Higher standard deviation usually implies higher consistency. Is the statement true or false?

Ans. False

Besant Technologies does the best and gives the best to all students for all courses. For our students, we care much about giving the detailed knowledge and making them be master and get placed in best companies. We prepare AI interview questions and answers for our students to placed and also for exam related questions. Here are the few samples AI interview questions and answers. So, the first thing is to get into this Artificial intelligence training in Chennai by Besant technologies and also to get online coaching in GangBoard.

Besant Technologies WhatsApp