(** 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
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
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
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
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
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
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. 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
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
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
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
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
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
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
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
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
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
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
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
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
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
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
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
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. 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?
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