Successfully reported this slideshow.
We use your LinkedIn profile and activity data to personalize ads and to show you more relevant ads. You can change your ad preferences anytime.

Artificial Intelligence (AI) Interview Questions and Answers | Edureka

297 views

Published on

(** Machine Learning Engineer Masters Program: https://www.edureka.co/masters-progra... **)
This PPT on Artificial Intelligence Interview Questions covers all the important concepts involved in the field of AI. This PPT is ideal for both beginners as well as professionals who want to learn or brush up their knowledge on AI concepts. Below are the topics covered in this tutorial:

1. Artificial Intelligence Basic Level Interview Question
2. Artificial Intelligence Intermediate Level Interview Question
3. Artificial Intelligence Scenario based Interview Question

Check out the entire Machine Learning Playlist: https://bit.ly/2NG9tK4

Follow us to never miss an update in the future.
YouTube: https://www.youtube.com/user/edurekaIN
Instagram: https://www.instagram.com/edureka_learning/
Facebook: https://www.facebook.com/edurekaIN/
Twitter: https://twitter.com/edurekain
LinkedIn: https://www.linkedin.com/company/edureka

Published in: Technology
  • Be the first to comment

Artificial Intelligence (AI) Interview Questions and Answers | Edureka

  1. 1. www.edureka.co/masters-program/machine-learning-engineer-training FIRST SLIDE
  2. 2. www.edureka.co/masters-program/machine-learning-engineer-training Artificial Intelligence (Basic) Interview Questions
  3. 3. www.edureka.co/masters-program/machine-learning-engineer-training Artificial Intelligence Interview Questions Whatisthedifference betweenAI, MachineLearningandDeep Learning? Question 1 Machine Learning Engineer Masters Program
  4. 4. www.edureka.co/masters-program/machine-learning-engineer-training Question 1 Whatisthedifference betweenAI, MachineLearningandDeep Learning? Machine Learning Engineer Masters Program Artificial Intelligence Interview Questions
  5. 5. www.edureka.co/masters-program/machine-learning-engineer-training WhatisArtificial Intelligence?Give anexampleofwhereAIisusedona dailybasis. Question 2 Artificial Intelligence Interview Questions Machine Learning Engineer Masters Program
  6. 6. www.edureka.co/masters-program/machine-learning-engineer-training Question 2 “Artificial intelligence (AI) is an area of computer science that emphasizes the creation of intelligent machines that work and react like humans.” “The capability of a machine to imitate the intelligent human behaviour.” WhatisArtificial Intelligence?Give anexampleofwhereAIisusedona dailybasis. Artificial Intelligence Interview Questions Machine Learning Engineer Masters Program
  7. 7. www.edureka.co/masters-program/machine-learning-engineer-training WhatarethedifferenttypesofAI? Question 3 Machine Learning Engineer Masters Program Artificial Intelligence Interview Questions
  8. 8. www.edureka.co/masters-program/machine-learning-engineer-training Question 3 WhatarethedifferenttypesofAI? Reactive Machines AI: Based on present actions, it cannot use previous experiences to form current decisions and simultaneously update their memory. Example: Deep Blue Limited Memory AI: Used in self-driving cars. They detect the movement of vehicles around them constantly and add it to their memory. Theory of Mind AI: Advanced AI that has the ability to understand emotions, people and other things in the real world. Self Aware AI: AIs that posses human like consciousness and reactions. Such machines have the ability to form self-driven actions. Artificial Narrow Intelligence (ANI): General purpose AI, used in building virtual assistants like Siri. Artificial General Intelligence (AGI): Also known as strong AI. An example is the Pillo robot that answers questions related to health. Artificial Superhuman Intelligence (ASI): AI that possesses the ability to do everything that a human can do and more. An example is the Alpha 2 which is the first humanoid ASI robot. Machine Learning Engineer Masters Program Artificial Intelligence Interview Questions
  9. 9. www.edureka.co/masters-program/machine-learning-engineer-training Explainthedifferentdomainsof ArtificialIntelligence. Question 4 Machine Learning Engineer Masters Program Artificial Intelligence Interview Questions
  10. 10. www.edureka.co/masters-program/machine-learning-engineer-training Question 4 Machine Learning Engineer Masters Program Explainthedifferentdomainsof ArtificialIntelligence. Machine Learning Neural Networks Robotics Expert Systems Fuzzy Logic Natural Language Processing Artificial Intelligence Interview Questions
  11. 11. www.edureka.co/masters-program/machine-learning-engineer-training HowisMachineLearningrelatedto ArtificialIntelligence? Question 5 Machine Learning Engineer Masters Program Artificial Intelligence Interview Questions
  12. 12. www.edureka.co/masters-program/machine-learning-engineer-training Question 5 Machine Learning is a subset of Artificial Intelligence. It is the science of getting computers to act by feeding them data and letting them learn a few tricks on their own, without being explicitly programmed to do so. HowisMachineLearningrelatedto ArtificialIntelligence? Machine Learning Engineer Masters Program Artificial Intelligence Interview Questions A technique that enables machines to mimic human behaviour Subset of AI which uses data to enable machines in solving problems Machine Learning Artificial Intelligence
  13. 13. www.edureka.co/masters-program/machine-learning-engineer-training Whatarethedifferenttypesof MachineLearning? Question 6 Machine Learning Engineer Masters Program Artificial Intelligence Interview Questions
  14. 14. www.edureka.co/masters-program/machine-learning-engineer-training Question 6 Machine Learning Engineer Masters Program Artificial Intelligence Interview Questions Whatarethedifferenttypesof MachineLearning? Supervised Learning Unsupervised Learning Reinforcement Learning
  15. 15. www.edureka.co/masters-program/machine-learning-engineer-training WhatisQ-Learning? Question 7 Machine Learning Engineer Masters Program Artificial Intelligence Interview Questions
  16. 16. www.edureka.co/masters-program/machine-learning-engineer-training Question 7 The Q-learning is a Reinforcement Learning algorithm in which an agent tries to learn the optimal policy from its past experiences with the environment. The past experiences of an agent are a sequence of state- action-rewards: WhatisQ-Learning? s0 a0 r1 s1 • s -> state • a -> action • r -> reward Agent was in State s0 and did Action a0, which resulted in it receiving Reward r1 and being in State s1 Machine Learning Engineer Masters Program Artificial Intelligence Interview Questions
  17. 17. www.edureka.co/masters-program/machine-learning-engineer-training Question 8 WhatisDeepLearning? Machine Learning Engineer Masters Program Artificial Intelligence Interview Questions
  18. 18. www.edureka.co/masters-program/machine-learning-engineer-training Question 8 WhatisDeepLearning? Deep learning mimics the way our brain functions i.e. it learns from experience. It uses the concept of neural networks to solve complex problems. Any Deep neural network will consist of three types of layers: • Input Layer • Hidden Layer • Output Layer Machine Learning Engineer Masters Program Artificial Intelligence Interview Questions
  19. 19. www.edureka.co/masters-program/machine-learning-engineer-training Question 9 Explainhowdeeplearningworks. Machine Learning Engineer Masters Program Artificial Intelligence Interview Questions
  20. 20. www.edureka.co/masters-program/machine-learning-engineer-training Question 9 Explainhowdeeplearningworks. • Deep Learning studies the basic unit of a brain called a brain cell or a neuron. Inspired from a neuron, an artificial neuron or a perceptron was developed. • A biological neuron, has dendrites which is used to receive inputs. • Similarly, a perceptron receives multiple inputs, applies various transformations and functions and provides an output. • Our brain consists of multiple connected neurons called neural network, we can also have a network of artificial neurons called perceptron's to form a Deep neural network. Machine Learning Engineer Masters Program Artificial Intelligence Interview Questions
  21. 21. www.edureka.co/masters-program/machine-learning-engineer-training Question 10 Explainthecommonlyused ArtificialNeuralNetworks. Machine Learning Engineer Masters Program Artificial Intelligence Interview Questions
  22. 22. www.edureka.co/masters-program/machine-learning-engineer-training Question 10 Explainthecommonlyused ArtificialNeuralNetworks. Feedforward Neural Network • Simplest form of ANN, where the data or the input travels in one direction. • The data passes through the input nodes and exit on the output nodes. This neural network may or may not have the hidden layers. Convolutional Neural Network • Here, input features are taken in batch wise like a filter. This will help the network to remember the images in parts and can compute the operations. • Mainly used for signal and image processing Machine Learning Engineer Masters Program Artificial Intelligence Interview Questions
  23. 23. www.edureka.co/masters-program/machine-learning-engineer-training Question 10 Explainthecommonlyused ArtificialNeuralNetworks. Recurrent Neural Network(RNN) – Long Short Term Memory • Works on the principle of saving the output of a layer and feeding this back to the input to help in predicting the outcome of the layer. • Here, you let the neural network to work on the front propagation and remember what information it needs for later use • This way each neuron will remember some information it had in the previous time-step. Autoencoders • These are unsupervised learning models with an input layer, an output layer and one or more hidden layers connecting them. • The output layer has the same number of units as the input layer. Its purpose is to reconstruct its own inputs. • Typically for the purpose of dimensionality reduction and for learning generative models of data. Machine Learning Engineer Masters Program Artificial Intelligence Interview Questions
  24. 24. www.edureka.co/masters-program/machine-learning-engineer-training Question 11 WhatareBayesianNetworks? Machine Learning Engineer Masters Program Artificial Intelligence Interview Questions
  25. 25. www.edureka.co/masters-program/machine-learning-engineer-training Question 11 WhatareBayesianNetworks? A Bayesian network is a statistical model that represents a set of variables and their conditional dependencies in the form of a directed acyclic graph. Symptoms Disease Probability Machine Learning Engineer Masters Program Artificial Intelligence Interview Questions
  26. 26. www.edureka.co/masters-program/machine-learning-engineer-training Question 12 Explaintheassessmentthatis usedtotesttheintelligenceofa machine. Machine Learning Engineer Masters Program Artificial Intelligence Interview Questions
  27. 27. www.edureka.co/masters-program/machine-learning-engineer-training Question 12 Explaintheassessmentthatis usedtotesttheintelligenceofa machine. In artificial intelligence (AI), a Turing Test is a method of inquiry for determining whether or not a computer is capable of thinking like a human being. Machine Learning Engineer Masters Program Artificial Intelligence Interview Questions
  28. 28. www.edureka.co/masters-program/machine-learning-engineer-training Artificial Intelligence (Intermediate) Interview Questions
  29. 29. www.edureka.co/masters-program/machine-learning-engineer-training HowdoesReinforcementLearning work?Explainwithanexample. Question 13 Machine Learning Engineer Masters Program Artificial Intelligence Interview Questions
  30. 30. www.edureka.co/masters-program/machine-learning-engineer-training Question 13 Machine Learning Engineer Masters Program Artificial Intelligence Interview Questions HowdoesReinforcementLearning work?Explainwithanexample. 1. The RL Agent (Player1) collects state S⁰ from the environment 2. Based on the state S⁰, the RL agent takes an action A⁰, initially the action is random 3. The environment is now in a new state S¹ 4. RL agent now gets a reward R¹ from the environment 5. The RL loop goes on until the RL agent is dead or reaches the destination
  31. 31. www.edureka.co/masters-program/machine-learning-engineer-training ExplainMarkov’sdecisionprocess withanexample. Question 14 Machine Learning Engineer Masters Program Artificial Intelligence Interview Questions
  32. 32. www.edureka.co/masters-program/machine-learning-engineer-training ExplainMarkov’sdecisionprocess withanexample. The mathematical approach for mapping a solution in reinforcement learning is called Markov Decision Process (MDP) In this problem, • Set of states are denoted by nodes i.e. {A, B, C, D} • Action is to traverse from one node to another {A -> B, C -> D} • Reward is the cost represented by each edge • Policy is the path taken to reach the destination {A -> C -> D} Machine Learning Engineer Masters Program Artificial Intelligence Interview Questions Question 14
  33. 33. www.edureka.co/masters-program/machine-learning-engineer-training Explainrewardmaximizationin Reinforcement Learning. Question 15 Machine Learning Engineer Masters Program Artificial Intelligence Interview Questions
  34. 34. www.edureka.co/masters-program/machine-learning-engineer-training Explainrewardmaximizationin Reinforcement Learning. Reward maximization theory states that, a RL agent must be trained in such a way that, he takes the best action so that the reward is maximum. Agent Opponent Reward Machine Learning Engineer Masters Program Artificial Intelligence Interview Questions Question 15
  35. 35. www.edureka.co/masters-program/machine-learning-engineer-training Whatisexploitationand explorationtradeoff? Question 16 Machine Learning Engineer Masters Program Artificial Intelligence Interview Questions
  36. 36. www.edureka.co/masters-program/machine-learning-engineer-training Whatisexploitationand explorationtradeoff? • Exploitation is about using the already known exploited information to heighten the rewards • Exploration is about exploring and capturing more information about an environment Agent Opponent Reward Machine Learning Engineer Masters Program Artificial Intelligence Interview Questions Question 16
  37. 37. www.edureka.co/masters-program/machine-learning-engineer-training Whatisthedifference between parametric&non-parametric models? Question 17 Machine Learning Engineer Masters Program Artificial Intelligence Interview Questions
  38. 38. www.edureka.co/masters-program/machine-learning-engineer-training Whatisthedifference between parametric&non-parametric models? Machine Learning Engineer Masters Program Artificial Intelligence Interview Questions Question 17
  39. 39. www.edureka.co/masters-program/machine-learning-engineer-training Question 18 Whatisthedifference between Hyperparametersandmodel parameters? Machine Learning Engineer Masters Program Artificial Intelligence Interview Questions
  40. 40. www.edureka.co/masters-program/machine-learning-engineer-training Whatisthedifference between Hyperparametersandmodel parameters? Model Parameters Hyperparameters Model parameters are the features of training data that will learn on its own during training. Model Hyperparameters are the parameters that determine the entire training process. For example, • Weights and Biases • Split points in Decision Tree For example, • Learning Rate • Hidden Layers • Hidden Units They are internal to the model and their value can be estimated from data. They are external to the model and their value cannot be estimated from data. Machine Learning Engineer Masters Program Artificial Intelligence Interview Questions Question 18
  41. 41. www.edureka.co/masters-program/machine-learning-engineer-training Question 19 WhatarehyperparametersinDeep NeuralNetworks? Machine Learning Engineer Masters Program Artificial Intelligence Interview Questions
  42. 42. www.edureka.co/masters-program/machine-learning-engineer-training WhatarehyperparametersinDeep NeuralNetworks? • Hyperparameters are the variables which define the structure of the network and the variables such as the learning rate, which define how the network is trained. • They determine the number of ideal hidden layers that must be present in a network. • More hidden units within a layer with regularization techniques can increase the accuracy of the network, whereas lesser number of units may cause underfitting. Machine Learning Engineer Masters Program Artificial Intelligence Interview Questions Hyperparameters Question 19
  43. 43. www.edureka.co/masters-program/machine-learning-engineer-training Question 20 Explainthedifferentalgorithms usedforhyperparameter optimization. Machine Learning Engineer Masters Program Artificial Intelligence Interview Questions
  44. 44. www.edureka.co/masters-program/machine-learning-engineer-training Explainthedifferentalgorithms usedforhyperparameter optimization. Grid Search Grid search trains the network for every combination by using the two set of hyperparameters, learning rate and number of layers. Then evaluates the model by using Cross Validation techniques. Random Search It randomly samples the search space and evaluates sets from a particular probability distribution. For example, instead of checking all 10,000 samples, randomly selected 100 parameters can be checked. Bayesian Optimization This includes fine tuning the hyperparameters by enabling automated model tuning. The model used for approximating the objective function is called surrogate model (Gaussian Process). Bayesian Optimization uses Gaussian Process (GP) function to get posterior functions to make predictions based on prior functions. Machine Learning Engineer Masters Program Artificial Intelligence Interview Questions Question 20
  45. 45. www.edureka.co/masters-program/machine-learning-engineer-training Howdoesdataoverfitting occur andhowcanitbefixed? Question 21 Machine Learning Engineer Masters Program Artificial Intelligence Interview Questions
  46. 46. www.edureka.co/masters-program/machine-learning-engineer-trainingMachine Learning Engineer Masters Program Artificial Intelligence Interview Questions Howdoesdataoverfitting occur andhowcanitbefixed? Overfitting occurs when a statistical model or machine learning algorithm captures the noise of the data. This causes an algorithm to show low bias but high variance in the outcome. How to Prevent Overfitting: ❑ Cross – validation ❑More training data ❑Remove features ❑Early stopping ❑Regularization ❑Use Ensemble models Question 21
  47. 47. www.edureka.co/masters-program/machine-learning-engineer-training Question 22 Mentionatechniquethathelpsto avoidoverfittinginaneural network. Machine Learning Engineer Masters Program Artificial Intelligence Interview Questions
  48. 48. www.edureka.co/masters-program/machine-learning-engineer-training Mentionatechniquethathelpsto avoidoverfittinginaneural network. Dropout is a type of regularization technique used to avoid overfitting in a neural network. It is a technique where randomly selected neurons are dropped during training. • Dropout value of approx 20%-50% of neurons with 20% providing a good starting point. Too low value has minimal effect and a value too high results in under-learning by the network. • Dropout regularization used on a larger network, gives the model more of an opportunity to learn independent representations. Machine Learning Engineer Masters Program Artificial Intelligence Interview Questions Question 22
  49. 49. www.edureka.co/masters-program/machine-learning-engineer-training Question 23 WhatisthepurposeofDeep Learningframeworkssuchas Keras,TensorFlowandPyTorch? Machine Learning Engineer Masters Program Artificial Intelligence Interview Questions
  50. 50. www.edureka.co/masters-program/machine-learning-engineer-training WhatisthepurposeofDeep Learningframeworkssuchas Keras,TensorFlowandPyTorch? Keras is an open source neural network library written in Python. It is designed to enable fast experimentation with deep neural networks. TensorFlow is an open-source software library for dataflow programming. It is used for machine learning applications like neural networks. PyTorch is an open source machine learning library for Python, based on Torch. It is used for applications such as natural language processing Machine Learning Engineer Masters Program Artificial Intelligence Interview Questions Question 23
  51. 51. www.edureka.co/masters-program/machine-learning-engineer-training Question 24 Differentiate betweenNLPandText mining Machine Learning Engineer Masters Program Artificial Intelligence Interview Questions
  52. 52. www.edureka.co/masters-program/machine-learning-engineer-training Differentiate betweenNLPandText mining Text Mining Natural Language Processing Aim of text mining is to extract useful insights from structured & un-structured text. Aim of NLP is to understand what is conveyed in speech. Text Mining can be done using text processing languages like Perl, statistical models, etc. NLP can be achieved using advanced machine learning models, deep neural networks, etc. Outcome: • Frequency of words • Patterns • Correlations Outcome: • Semantic meaning of text • Sentimental analysis • Grammatical structure Machine Learning Engineer Masters Program Artificial Intelligence Interview Questions Question 24
  53. 53. www.edureka.co/masters-program/machine-learning-engineer-training Question 25 Whatarethedifferentcomponents ofNLP? Machine Learning Engineer Masters Program Artificial Intelligence Interview Questions
  54. 54. www.edureka.co/masters-program/machine-learning-engineer-training Whatarethedifferentcomponents ofNLP? Natural Language Understanding Natural Language Generation Natural Language Understanding includes: • Mapping input to useful representations • Analysing different aspects of the language Natural Language Generation includes: • Text Planning • Sentence Planning • Text Realization Machine Learning Engineer Masters Program Artificial Intelligence Interview Questions Question 25
  55. 55. www.edureka.co/masters-program/machine-learning-engineer-training Question 26 WhatisStemming&Lemmatization inNLP? Machine Learning Engineer Masters Program Artificial Intelligence Interview Questions
  56. 56. www.edureka.co/masters-program/machine-learning-engineer-training WhatisStemming&Lemmatization inNLP? Stemming Lemmatization Machine Learning Engineer Masters Program Artificial Intelligence Interview Questions Question 26
  57. 57. www.edureka.co/masters-program/machine-learning-engineer-training Question 27 ExplainFuzzyLogicarchitecture. Machine Learning Engineer Masters Program Artificial Intelligence Interview Questions
  58. 58. www.edureka.co/masters-program/machine-learning-engineer-training 1. Fuzzification Module − It transforms the system inputs, which are crisp numbers, into fuzzy sets. 2. Knowledge Base − It stores IF-THEN rules provided by experts. 3. Inference Engine − It simulates the human reasoning process by making fuzzy inference on the inputs and IF-THEN rules. 4. Defuzzification Module − It transforms the fuzzy set obtained by the inference engine into a crisp value. ExplainFuzzyLogicarchitecture. Machine Learning Engineer Masters Program Artificial Intelligence Interview Questions Question 27
  59. 59. www.edureka.co/masters-program/machine-learning-engineer-training Question 28 ExplainthecomponentsofExpert Systems Machine Learning Engineer Masters Program Artificial Intelligence Interview Questions
  60. 60. www.edureka.co/masters-program/machine-learning-engineer-training ExplainthecomponentsofExpert Systems Knowledge Base Inference Engine User Interface Expert System Knowledge Base • It contains domain-specific and high-quality knowledge. Inference Engine • It acquires and manipulates the knowledge from the knowledge base to arrive at a particular solution. User Interface • User interface provides interaction between user of the ES and the ES itself. User Machine Learning Engineer Masters Program Artificial Intelligence Interview Questions Question 28
  61. 61. www.edureka.co/masters-program/machine-learning-engineer-training Question 29 HowisComputerVisionandAI related? Machine Learning Engineer Masters Program Artificial Intelligence Interview Questions
  62. 62. www.edureka.co/masters-program/machine-learning-engineer-training Question 29 HowisComputerVisionandAI related? Computer Vision is a field of Artificial Intelligence that is used to obtain information from images or multi-dimensional data. Machine Learning Engineer Masters Program Artificial Intelligence Interview Questions
  63. 63. www.edureka.co/masters-program/machine-learning-engineer-training Question 30 Whichisbetterforimage classification? Supervisedor unsupervisedclassification. Justify. Machine Learning Engineer Masters Program Artificial Intelligence Interview Questions
  64. 64. www.edureka.co/masters-program/machine-learning-engineer-training Question 30 Whichisbetterforimage classification? Supervisedor unsupervisedclassification. Justify. Supervised Classification? Unsupervised Classification? • In supervised classification, the images are interpreted manually by the ML expert to create feature classes • In unsupervised classification the ML software creates feature classes based on image pixel values. • Therefore, it is better to opt for supervised classification for image classification in terms of accuracy. Machine Learning Engineer Masters Program Artificial Intelligence Interview Questions
  65. 65. www.edureka.co/masters-program/machine-learning-engineer-training Finitedifferencefiltersinimage processingareverysusceptibleto noise.Tocopeupwiththis,which methodcanyouusesothatthere wouldbeminimaldistortionsby noise? Question 31 Machine Learning Engineer Masters Program Artificial Intelligence Interview Questions
  66. 66. www.edureka.co/masters-program/machine-learning-engineer-training Question 31 Finitedifferencefiltersinimage processingareverysusceptibleto noise.Tocopeupwiththis,which methodcanyouusesothatthere wouldbeminimaldistortionsby noise? Image Smoothing is one of the best methods used for reducing noise by forcing pixels to be more like their neighbours. Machine Learning Engineer Masters Program Artificial Intelligence Interview Questions
  67. 67. www.edureka.co/masters-program/machine-learning-engineer-training HowisGametheoryandAIrelated? Question 32 Machine Learning Engineer Masters Program Artificial Intelligence Interview Questions
  68. 68. www.edureka.co/masters-program/machine-learning-engineer-training Question 32 HowisGametheoryandAIrelated? “In the context of artificial intelligence(AI) and deep learning systems, game theory is essential to enable some of the key capabilities required in multi-agent environments in which different AI programs need to interact or compete in order to accomplish a goal.” Machine Learning Engineer Masters Program Artificial Intelligence Interview Questions
  69. 69. www.edureka.co/masters-program/machine-learning-engineer-training Question 33 WhatistheMinimaxAlgorithm? Explaintheterminologies involved inaMinimaxproblem. Machine Learning Engineer Masters Program Artificial Intelligence Interview Questions
  70. 70. www.edureka.co/masters-program/machine-learning-engineer-training Question 33 WhatistheMinimaxAlgorithm? Explaintheterminologies involved inaMinimaxproblem. Minimax is a recursive algorithm used to choose an optimal move for a player assuming that the other player is also playing optimally. A game can be defined as a search problem with the following components: • Game Tree: A tree structure containing all the possible moves. • Initial state: The initial position of the board and showing whose move it is. • Successor function: It defines the possible legal moves a player can make. • Terminal state: It is the position of the board when the game ends. • Utility function: It is a function which assigns a numeric value for the outcome of a game. Machine Learning Engineer Masters Program Artificial Intelligence Interview Questions
  71. 71. www.edureka.co/masters-program/machine-learning-engineer-training Artificial Intelligence Scenario Based Interview Questions
  72. 72. www.edureka.co/masters-program/machine-learning-engineer-training ShowtheworkingoftheMinimax algorithmusingTic-Tac-ToeGame. Question 34 Machine Learning Engineer Masters Program Artificial Intelligence Interview Questions
  73. 73. www.edureka.co/masters-program/machine-learning-engineer-training Question 34 ShowtheworkingoftheMinimax algorithmusingTic-Tac-ToeGame. Step 1: First, generate the entire game tree starting with the current position of the game all the way upto the terminal states. There are two players involved in a game: 1. MAX: This player tries to get the highest possible score 2. MIN: MIN tries to get the lowest possible score Machine Learning Engineer Masters Program Artificial Intelligence Interview Questions
  74. 74. www.edureka.co/masters-program/machine-learning-engineer-training ShowtheworkingoftheMinimax algorithmusingTic-Tac-ToeGame. Step 2: Apply the utility function to get the utility values for all the terminal states. Step 3: Determine the utilities of the higher nodes with the help of the utilities of the terminal nodes. For instance, in the diagram below, we have the utilities for the terminal states written in the squares. Machine Learning Engineer Masters Program Artificial Intelligence Interview Questions Question 34
  75. 75. www.edureka.co/masters-program/machine-learning-engineer-training ShowtheworkingoftheMinimax algorithmusingTic-Tac-ToeGame. Let us calculate the utility for the left node(red) of the layer above the terminal: MIN{3, 5, 10}, i.e. 3. Therefore, utility for red node is 3. Similarly, for the green node in the same layer: MIN{2,2}, i.e. 2. Machine Learning Engineer Masters Program Artificial Intelligence Interview Questions Question 34
  76. 76. www.edureka.co/masters-program/machine-learning-engineer-training ShowtheworkingoftheMinimax algorithmusingTic-Tac-ToeGame. Step 4: Calculate the utility values. Step 5: Eventually, all the backed-up values reach to the root of the tree. At that point, MAX has to choose the highest value: i.e. MAX{3,2} which is 3. Therefore, the best opening move for MAX is the left node(or the red one). To summarize, Minimax Decision = MAX{MIN{3,5,10},MIN{2,2}} = MAX{3,2} = 3 Machine Learning Engineer Masters Program Artificial Intelligence Interview Questions Question 34
  77. 77. www.edureka.co/masters-program/machine-learning-engineer-training Whichmethodisusedfor optimizingaMinimaxbasedgame? Question 35 Machine Learning Engineer Masters Program Artificial Intelligence Interview Questions
  78. 78. www.edureka.co/masters-program/machine-learning-engineer-training Question 35 Whichmethodisusedfor optimizingaMinimaxbasedgame? Alpha-beta Pruning If we apply alpha-beta pruning to a standard minimax algorithm, it returns the same move as the standard one, but it removes all the nodes that are possibly not affecting the final decision. In this case, Minimax Decision = MAX{MIN{3,5,10}, MIN{2,a,b}, MIN{2,7,3}} = MAX{3,c,2} = 3 Hint: (MIN{2,a,b} would certainly be less than or equal to 2, i.e., c<=2 and hence MAX{3,c,2} has to be 3.) Machine Learning Engineer Masters Program Artificial Intelligence Interview Questions
  79. 79. www.edureka.co/masters-program/machine-learning-engineer-training WhichalgorithmdoesFacebookuse forfaceverification? Question 36 Machine Learning Engineer Masters Program Artificial Intelligence Interview Questions
  80. 80. www.edureka.co/masters-program/machine-learning-engineer-training Question 36 WhichalgorithmdoesFacebookuse forfaceverificationandhowdoes itwork? DeepFace tool works on face verification algorithm, structured by Artificial Intelligence (AI) techniques using neural network models. Input: Scan a wild form of photos with large complex data Process: In modern face recognition, the process completes in 4 raw steps: • Detect • Align • Represent • Classify Output: Final result is a face representation, which is derived from a 9-layer deep neural net Training Data: More than 4 million facial images of more than 4000 people Result: Facebook can detect whether the two images represent the same person or not Machine Learning Engineer Masters Program Artificial Intelligence Interview Questions
  81. 81. www.edureka.co/masters-program/machine-learning-engineer-training Explainthelogicbehindtargeted marketing. HowcanMachine Learninghelpwiththis? Question 37 Machine Learning Engineer Masters Program Artificial Intelligence Interview Questions
  82. 82. www.edureka.co/masters-program/machine-learning-engineer-training Question 37 Explainthelogicbehindtargeted marketing. HowcanMachine Learninghelpwiththis? Target Marketing involves breaking a market into segments & concentrating it on a few key segments consisting of the customers whose needs and desires most closely match your product. Machine Learning in targeted marketing: • Text Analytics Systems • Clustering • Classification • Recommender Systems • Market Basket Analysis Machine Learning Engineer Masters Program Artificial Intelligence Interview Questions
  83. 83. www.edureka.co/masters-program/machine-learning-engineer-training HowcanAIbeusedindetecting fraud? Question 38 Machine Learning Engineer Masters Program Artificial Intelligence Interview Questions
  84. 84. www.edureka.co/masters-program/machine-learning-engineer-training Question 38 HowcanAIbeusedindetecting fraud? Artificial Intelligence is used in Fraud detection problems by implementing Machine Learning algorithms for detecting anomalies and studying hidden patterns in data. The following approach is followed for detecting fraudulent activities: 1. Data Extraction 2. Data Cleaning 3. Data Exploration & Analysis 4. Building a Machine Learning model 5. Model Evaluation Data Collection Data Cleaning Exploration & Analysis Building a Model Model Evaluation Machine Learning Engineer Masters Program Artificial Intelligence Interview Questions
  85. 85. www.edureka.co/masters-program/machine-learning-engineer-training Abankmanagerisgivenadataset containingrecordsof1000sof applicantswhohaveappliedfora loan.HowcanAIhelpthemanager understandwhichloanshecan approve?Explain. Question 39 Machine Learning Engineer Masters Program Artificial Intelligence Interview Questions
  86. 86. www.edureka.co/masters-program/machine-learning-engineer-training Abankmanagerisgivenadataset containingrecordsof1000sof applicantswhohaveappliedfora loan.HowcanAIhelpthemanager understandwhichloanshecan approve?Explain. This problem statement can be solved using the KNN algorithm that will classify the applicant's loan request into two classes: • Approved • Disapproved • K Nearest Neighbour is a Supervised Learning algorithm that classifies a new data point into the target class, depending on the features of it’s neighbouring data points. Data Collection Data Cleaning Exploration & Analysis Building a Model Model Evaluation Machine Learning Engineer Masters Program Artificial Intelligence Interview Questions Question 39
  87. 87. www.edureka.co/masters-program/machine-learning-engineer-training Placeanagentinanyoneofthe rooms(0,1,2,3,4)andthegoalisto reachoutsidethebuilding(room5). CanthisbeachievedthroughAI?If yes,explainhowitcanbedone. Question 40 0 4 3 1 2 5 • 5 rooms in a building connected by doors • Each room is numbered 0 through 4 • The outside of the building can be thought of as one big room (5) • Doors 1 and 4 directly lead to room 5 (outside) Machine Learning Engineer Masters Program Artificial Intelligence Interview Questions
  88. 88. www.edureka.co/masters-program/machine-learning-engineer-training Placeanagentinanyoneofthe rooms(0,1,2,3,4)andthegoalisto reachoutsidethebuilding(room5). CanthisbeachievedthroughAI?If yes,explainhowitcanbedone. This problem can be solved by using the Q-Learning algorithm, which is a reinforcement learning algorithm used to solve reward based problems. Let’s represent the rooms on a graph, each room as a node, and each door as a link Machine Learning Engineer Masters Program Artificial Intelligence Interview Questions Question 40
  89. 89. www.edureka.co/masters-program/machine-learning-engineer-training Placeanagentinanyoneofthe rooms(0,1,2,3,4)andthegoalisto reachoutsidethebuilding(room5). CanthisbeachievedthroughAI?If yes,explainhowitcanbedone. Next step is to associate a reward value to each door: • doors that lead directly to the goal have a reward of 100 • Doors not directly connected to the target room have zero reward • Because doors are two-way, two arrows are assigned to each room • Each arrow contains an instant reward value Machine Learning Engineer Masters Program Artificial Intelligence Interview Questions Question 40
  90. 90. www.edureka.co/masters-program/machine-learning-engineer-training Placeanagentinanyoneofthe rooms(0,1,2,3,4)andthegoalisto reachoutsidethebuilding(room5). CanthisbeachievedthroughAI?If yes,explainhowitcanbedone. The terminology in Q-Learning includes the terms state and action: • Room (including room 5) represents a state • Agent’s movement from one room to another represents an action • In the figure, a state is depicted as a node, while "action" is represented by the arrows Example (Agent traverse from room 2 to room5): 1. Initial state = state 2 2. State 2 -> state 3 3. State 3 -> state (2, 1, 4) 4. State 4 -> state 5 Machine Learning Engineer Masters Program Artificial Intelligence Interview Questions Question 40
  91. 91. www.edureka.co/masters-program/machine-learning-engineer-training Placeanagentinanyoneofthe rooms(0,1,2,3,4)andthegoalisto reachoutsidethebuilding(room5). CanthisbeachievedthroughAI?If yes,explainhowitcanbedone. We can put the state diagram and the instant reward values into a reward table, matrix R. Machine Learning Engineer Masters Program Artificial Intelligence Interview Questions Question 40
  92. 92. www.edureka.co/masters-program/machine-learning-engineer-training Placeanagentinanyoneofthe rooms(0,1,2,3,4)andthegoalisto reachoutsidethebuilding(room5). CanthisbeachievedthroughAI?If yes,explainhowitcanbedone. Add another matrix Q, representing the memory of what the agent has learned through experience. • The rows of matrix Q represent the current state of the agent • columns represent the possible actions leading to the next state • Formula to calculate the Q matrix: Q(state, action) = R(state, action) + Gamma * Max [Q(next state, all actions)] The Gamma parameter has a range of 0 to 1 (0 <= Gamma > 1). • If Gamma is closer to zero, the agent will tend to consider only immediate rewards. • If Gamma is closer to one, the agent will consider future rewards with greater weight Note Machine Learning Engineer Masters Program Artificial Intelligence Interview Questions Question 40
  93. 93. www.edureka.co/masters-program/machine-learning-engineer-training Placeanagentinanyoneofthe rooms(0,1,2,3,4)andthegoalisto reachoutsidethebuilding(room5). CanthisbeachievedthroughAI?If yes,explainhowitcanbedone. Using Q – Learning algorithm to solve the problem: Machine Learning Engineer Masters Program Artificial Intelligence Interview Questions Question 40
  94. 94. www.edureka.co/masters-program/machine-learning-engineer-training You’vewona2-million-dollar worthlottery’weallgetsuchspam messages.HowcanAIbeusedto detectandfilteroutsuchspam messages? Question 41 Machine Learning Engineer Masters Program Artificial Intelligence Interview Questions
  95. 95. www.edureka.co/masters-program/machine-learning-engineer-training You’vewona2-million-dollar worthlottery’weallgetsuchspam messages.HowcanAIbeusedto detectandfilteroutsuchspam messages? Data Collection Data Cleaning Data Exploration & Analysis Data Modelling Model Evaluation Optimization Deployment Gmail makes use of machine learning to filter out such spam messages from our inbox. These spam filters are used to classify emails into two classes, namely spam and non-spam emails. Let’s understand how spam detection is done using machine learning: Machine Learning Engineer Masters Program Artificial Intelligence Interview Questions Question 41
  96. 96. www.edureka.co/masters-program/machine-learning-engineer-training Let’ssaythatyoustartedan onlineshoppingbusinessandto growyourbusiness,youwantto forecastthesalesfortheupcoming months.Howwouldyoudothis? Explain. Question 42 Machine Learning Engineer Masters Program Artificial Intelligence Interview Questions
  97. 97. www.edureka.co/masters-program/machine-learning-engineer-training Let’ssaythatyoustartedan onlineshoppingbusinessandto growyourbusiness,youwantto forecastthesalesfortheupcoming months.Howwouldyoudothis? Explain. Predicted sales Actual sales Time Sales When both price and time period have a linear relationship, use simple linear regression. Linear Regression is a method to predict dependent variable (Y) based on values of independent variables (X). It can be used for the cases where we want to predict some continuous quantity. Machine Learning Engineer Masters Program Artificial Intelligence Interview Questions Question 42
  98. 98. www.edureka.co/masters-program/machine-learning-engineer-training Let’ssaythatyoustartedan onlineshoppingbusinessandto growyourbusiness,youwantto forecastthesalesfortheupcoming months.Howwouldyoudothis? Explain. • Dependent variable (Y): The response variable whose value needs to be predicted. • Independent variable (X): The predictor variable used to predict the response variable. The following equation is used to represent a linear regression model: x y independent variable dependentvariable Y= 𝒃 𝟎 + 𝒃 𝟏 𝒙 + ⅇ Machine Learning Engineer Masters Program Artificial Intelligence Interview Questions Question 42
  99. 99. www.edureka.co/masters-program/machine-learning-engineer-training Let’ssaythatyoustartedan onlineshoppingbusinessandto growyourbusiness,youwantto forecastthesalesfortheupcoming months.Howwouldyoudothis? Explain. Y= 𝒃 𝟎 + 𝒃 𝟏 𝒙 + ⅇ dependent variable Y intercept Slope independent variable Error Machine Learning Engineer Masters Program Artificial Intelligence Interview Questions Question 42
  100. 100. www.edureka.co/masters-program/machine-learning-engineer-training ‘Customerswhoboughtthis,also boughtthis…’weoftenseethis whenweshoponAmazon.Whatis thelogicbehindrecommendation engines? Question 43 Machine Learning Engineer Masters Program Artificial Intelligence Interview Questions
  101. 101. www.edureka.co/masters-program/machine-learning-engineer-training ‘Customerswhoboughtthis,also boughtthis…’weoftenseethis whenweshoponAmazon.Whatis thelogicbehindrecommendation engines? Collaborative filtering is the process of comparing users with similar shopping behaviours in order to recommend products to a new user with similar shopping behaviour. Machine Learning Engineer Masters Program Artificial Intelligence Interview Questions Question 43
  102. 102. www.edureka.co/masters-program/machine-learning-engineer-training Question 44 Whatismarketbasketanalysisand howcanArtificial Intelligencebe usedtoperformthis? Machine Learning Engineer Masters Program Artificial Intelligence Interview Questions
  103. 103. www.edureka.co/masters-program/machine-learning-engineer-training Question 44 Market basket analysis explains the combinations of products that frequently co-occur in transactions. Market Basket Analysis algorithms: 1. Association Rule Mining 2. Apriori Machine Learning Engineer Masters Program Artificial Intelligence Interview Questions Whatismarketbasketanalysisand howcanArtificial Intelligencebe usedtoperformthis?
  104. 104. www.edureka.co/masters-program/machine-learning-engineer-training Question 44 • Association rule mining is a technique that shows how items are associated to each other. • Apriori algorithm uses frequent item sets to generate association rules. It is based on the concept that a subset of a frequent itemset must also be a frequent itemset. A B Example of Association rule: ➢ It means that if a person buys item A then he will also buy item B Customer who purchase bread have a 60% likelihood of also purchasing jam. Machine Learning Engineer Masters Program Artificial Intelligence Interview Questions Whatismarketbasketanalysisand howcanArtificial Intelligencebe usedtoperformthis?
  105. 105. www.edureka.co/masters-program/machine-learning-engineer-training Question 45 ThecropyieldinIndiaisdegrading becausefarmersareunableto detectdiseasesincropsduringthe earlystages.CanAIbeusedfor diseasedetection incrops?Ifyes, explain. Machine Learning Engineer Masters Program Artificial Intelligence Interview Questions
  106. 106. www.edureka.co/masters-program/machine-learning-engineer-training Question 45 ThecropyieldinIndiaisdegrading becausefarmersareunableto detectdiseasesincropsduringthe earlystages.CanAIbeusedfor diseasedetection incrops?Ifyes, explain. AI can be used to implement image analysis and classification techniques for extraction and classification of leaf diseases. Image Acquisition Image Pre- processing Image Segmentation Feature Extraction Classification Machine Learning Engineer Masters Program Artificial Intelligence Interview Questions
  107. 107. www.edureka.co/masters-program/machine-learning-engineer-training Question 45 ThecropyieldinIndiaisdegrading becausefarmersareunableto detectdiseasesincropsduringthe earlystages.CanAIbeusedfor diseasedetection incrops?Ifyes, explain. • Image Acquisition: The sample images are collected and stored as input database. • Image Pre-processing: Aim is to improve image data that suppress undesired distortions as well as enhance specific image features. Image enhancement Colorspace conversion • YCbCr • L*a*b* • Image Segmentation: The goal is to simplify and modify an image into something that is easier to analyse. K- means clustering algorithm is used for segmentation of the images. • Feature Extraction: To extract the information that can be used to find the significance of a given sample. The Gray-Level Co-Occurrence Matrix can be used here. • Classification: Linear Support Vector Algorithm is used for classification of leaf disease. SVM is a binary classifier which uses a hyper plane called the decision boundary between two classes Machine Learning Engineer Masters Program Artificial Intelligence Interview Questions

×