[REAL TIME] Artificial Intelligence (AI) Interview Question & Answer
Artificial Intelligence Interview Questions and Answers

[REAL TIME] Artificial Intelligence (AI) Interview Question & Answer

Last updated on 04th Jul 2020, Blog, Interview Questions

About author

Rupan (Sr Director - Artificial Intelligence )

He is a Proficient Technical Expert for Respective Industry Domain & Serving 8+ Years. Also, Dedicated to Imparts the Informative Knowledge's to Freshers. He Share's this Blogs for us.

(5.0) | 16547 Ratings 2919

Whether it’s a career that you are considering, or you want to move up the ladder from where you already are – in the AI domain, the future definitely is bright. There are numerous professionals, alongside you, who have recognized the opportunities to move into the field. Considering the competition in this sphere, to position yourself as a successful job candidate who stands out from a crowd. Hence, it is a good idea to not only pursue certifications in Artificial Intelligence, but also prepare ahead of time for crucial job AI interview questions. Here are some commonly asked ones that will assist you in preparing for the same. 

1).What is Artificial Intelligence?

Ans:

Artificial Intelligence is an area of computer science that emphasizes the creation of intelligent machines that work and reacts like humans.

2).What is an artificial intelligence Neural Network?

Ans:

Artificial intelligence Neural Networks can model mathematically the way biological brains work, allowing the machine to think and learn the same way the humans do- making them capable of recognizing things like speech, objects and animals like we do.

3).What are the various areas where AI (Artificial Intelligence) can be used?

Ans:

Artificial Intelligence can be used in many areas like Computing, Speech recognition, Bioinformatics, Humanoid robot, Computer software, Space and Aeronautics etc.

4).Which is not a commonly used programming language for AI?

Ans:

Perl language is not commonly used programming language for AI

5).What is Prolog in AI?

Ans:

In AI, Prolog is a programming language based on logic.

6).Give an explanation on the difference between strong AI and weak AI?

Ans:

Strong AI makes strong claims that computers can be made to think on a level equal to humans while weak AI simply predicts that some features that are resembling human intelligence can be incorporated to computers to make them more useful tools.

7).Mention the difference between statistical AI and Classical AI ?

Ans:

Statistical AI is more concerned with “inductive” thought like given a set of patterns, induce the trend etc.  While, classical AI, on the other hand, is more concerned with “ deductive” thought given as a set of constraints, deduce a conclusion etc.

8).What is alternate, artificial, compound and natural key?

Ans:

  • Alternate Key: Excluding primary keys all candidate keys are known as Alternate Keys.
  • Artificial Key: If no obvious key either stands alone or compound is available, then the last resort is to simply create a key, by assigning a number to each record or occurrence.  This is known as an artificial key.
  • Compound Key: When there is no single data element that uniquely defines the occurrence within a construct, then integrating multiple elements to create a unique identifier for the construct is known as Compound Key.
  • Natural Key: Natural key is one of the data elements that is stored within a construct, and which is utilized as the primary key.

9).What does a production rule consist of?

Ans:

The production rule comprises a set of rules and a sequence of steps.

10).Which search method takes less memory?

Ans:

The “depth first search” method takes less memory.

11).Which is the best way to go for Game playing problem?

Ans:

Heuristic approach is the best way to go for game playing problem, as it will use the technique based on intelligent guesswork. For example, Chess between humans and computers as it will use brute force computation, looking at hundreds of thousands of positions.

12).A* algorithm is based on which search method?

Ans:

A* algorithm is based on best first search method, as it gives an idea of optimization and quick choose of path, and all characteristics lie in A* algorithm.

13).What does a hybrid Bayesian network contain?

Ans:

A hybrid Bayesian network contains both a discrete and continuous variables.

14).What is agent in artificial intelligence?

Ans:

Anything perceives its environment by sensors and acts upon an environment by effectors are known as Agent. Agent includes Robots, Programs, and Humans etc.

15).What does Partial order or planning involve?

Ans:

In partial order planning , rather than searching over possible situation it involves searching over the space of possible plans.  The idea is to construct a plan piece by piece.

16).What are the two different kinds of steps that we can take in constructing a plan?

Ans:

  • Add an operator (action)
  • Add an ordering constraint between operators

17).Which property is considered as not a desirable property of a logical rule-based system?

Ans:

“Attachment” is considered as not a desirable property of a logical rule based system.

18).What is the Neural Network in Artificial Intelligence?

Ans:

In artificial intelligence, a neural network is an emulation of a biological neural system, which receives the data, processes the data and gives the output based on the algorithm and empirical data.

19).When an algorithm is considered completed?

Ans:

An algorithm is said to be complete when it terminates with a solution when one exists.

20).What is a heuristic function?

Ans:

A heuristic function ranks alternatives, in search algorithms, at each branching step based on the available information to decide which branch to follow.

    Subscribe For Free Demo

    21).What is the function of the third component of the planning system?

    Ans:

    In a planning system, the function of the third component is to detect when a solution to a problem has been found.

    22).What is “Generality” in AI ?

    Ans:

    Generality is the measure of ease with which the method can be adapted to different domains of application.

    23).What is a top-down parser?

    Ans:

    A top-down parser begins by hypothesizing a sentence and successively predicting lower level constituents until individual pre-terminal symbols are written.

    24).Mention the difference between breadth first search and best first search in artificial intelligence?

    Ans:

    These are the two strategies which are quite similar. In best first search, we expand the nodes in accordance with the evaluation function. While, in breadth first search a node is expanded in accordance to the cost function of the parent node.

    25).What are frames and scripts in “Artificial Intelligence”?

    Ans:

    Frames are a 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 knowledge into substructure by representing “stereotyped situations’. Scripts are similar to frames, except the values that fill the slots must be ordered.  Scripts are used in natural language understanding systems to organize a knowledge base in terms of the situation that the system should understand.

    26).What does FOPL stand for and explain its role in Artificial Intelligence?

    Ans:

    FOPL stands for First Order Predicate Logic, Predicate Logic provides

    •   A language to express assertions about certain “World”
    •   An inference system to deductive apparatus whereby we may draw conclusions from such assertion
    •   A semantic based on set theory

    27).What does the language of FOPL consists of

    Ans:

    • A set of constant symbols
    •   A set of variables
    •   A set of predicate symbols
    •   A set of function symbols
    •   The logical connective
    •   The Universal Quantifier and Existential Quantifier
    • A special binary relation of equality

    28).For online search in ‘Artificial Intelligence’ which search agent operates by interleaving computation and action?

    Ans:

    In online search, it will first take action and then observe the environment.

    29).Which search algorithm will use a limited amount of memory in online search?

    Ans:

    RBFE and SMA* will solve any kind of problem that A* can’t by using a limited amount of memory.

    30).In ‘Artificial Intelligence’ where you can use the Bayes rule?

    Ans:

    In Artificial Intelligence to answer the probabilistic queries conditioned on one piece of evidence, Bayes rule can be used.

    Course Curriculum

    Enroll in Artificial Intelligence Training to Build Skills & Advance Your Career

    • Instructor-led Sessions
    • Real-life Case Studies
    • Assignments
    Explore Curriculum

    31)   For building a Bayes model how many terms are required?

    Ans:

    For building a Bayes model in AI, three terms are required; they are one conditional probability and two unconditional probability.

    32)   While creating the Bayesian Network what is the consequence between a node and its predecessors?

    Ans:

    While creating the Bayesian Network, the consequence between a node and its predecessors is that a node can be conditionally independent of its predecessors.

    33)   To answer any query how the Bayesian network can be used?

    Ans:

    If a Bayesian Network is a representative of the joint distribution, then by summing all the relevant joint entries, it can solve any query.

    34)   What combines inductive methods with the power of first order representations?

    Ans:

    Inductive logic programming combines inductive methods with the power of first order representations.

    35)   In Inductive Logic Programming what needed to be satisfied?

    Ans:

    The objective of an Inductive Logic Programming is to come up with a set of sentences for the hypothesis such that the entailment constraint is satisfied.

    36)   In top-down inductive learning methods how many literals are available?  What are they?

    Ans:

    There are three literals available in top-down inductive learning methods they are

    •   Predicates
    •   Equality and Inequality
    • Arithmetic Literals

    37)   Which algorithm inverts a complete resolution strategy?

    Ans:

    ‘Inverse Resolution’ inverts a complete resolution, as it is a complete algorithm for learning first order theories.

    38)   In speech recognition what kind of signal is used?

    Ans:

    In speech recognition, Acoustic signal is used to identify a sequence of words.

    39)   In speech recognition which model gives the probability of each word following each word?

    Ans:

    Biagram model gives the probability of each word following each other word in speech recognition.

    40)    Which algorithm is used for solving temporal probabilistic reasoning?

    Ans:

    To solve temporal probabilistic reasoning, HMM (Hidden Markov Model) is used, independent of transition and sensor model.

    41)   What Hidden Markov Model (HMMs) is used?

    Ans:

    Hidden Markov Models are a ubiquitous tool for modelling time series data or to model sequence behaviour.  They are used in almost all current speech recognition systems.

    42)   In the Hidden Markov Model, how does the state of the process is described?

    Ans:

    The state of the process in HMM’s model is described by a ‘Single Discrete Random Variable’.

    43)   In HMM’s, what are the possible values of the variable?

    Ans:

    ‘Possible States of the World’ is the possible values of the variable in HMM’s.

    44)   In HMM, where does the additional variable be added?

    Ans:

    While staying within the HMM network, the additional state variables can be added to a temporal model.

    45)   In Artificial Intelligence, what do semantic analyses used for?

    Ans:

    In Artificial Intelligence, to extract the meaning from the group of sentences semantic analysis is used.

    46)   What is meant by compositional semantics?

    Ans:

    The process of determining the meaning of P*Q from P,Q and* is known as Compositional Semantics.

    47)   How logical inference can be solved in Propositional Logic?

    Ans:

    In Propositional Logic, Logical Inference algorithm can be solved by using

    •   Logical Equivalence
    •   Validity
    •   Satisfying ability

    48)   Which process makes different logical expressions look identical?

    Ans:

    ‘Unification’ process makes different logical expressions identical.  Lifted inferences require finding substitutes which can make a different expression look identical.  This process is called unification.

    49)   Which algorithm in ‘Unification and Lifting’ takes two sentences and returns a unifier?

    Ans:

    In ‘Unification and Lifting’ the algorithm that takes two sentences and returns a unifier is ‘Unify’ algorithm.

    50)   Which is the most straightforward approach for planning algorithms?

    Ans:

    State space search is the most straightforward approach for planning algorithms because it takes account of everything for finding a solution.

    Course Curriculum

    Learn Artificial Intelligence Course and Get Hired By TOP MNCs

    Weekday / Weekend BatchesSee Batch Details

    51) What are the different types of AI?

    Ans:

    • 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 possess 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.

    52) Explain the different domains of Artificial Intelligence.

    Ans:

    domains-Artificial-Intelligence.
    • Machine Learning: It’s the science of getting computers to act by feeding them data so that they can learn a few tricks on their own, without being explicitly programmed to do so.
    • Neural Networks: They are a set of algorithms and techniques, modeled in accordance with the human brain. Neural Networks are designed to solve complex and advanced machine learning problems.
    • Robotics: Robotics is a subset of AI, which includes different branches and application of robots. These Robots are artificial agents acting in a real-world environment. An AI Robot works by manipulating the objects in its surrounding, by perceiving, moving and taking relevant actions.
    • Expert Systems: An expert system is a computer system that mimics the decision-making ability of a human. It is a computer program that uses artificial intelligence (AI) technologies to simulate the judgment and behavior of a human or an organization that has expert knowledge and experience in a particular field.
    • Fuzzy Logic Systems: Fuzzy logic is an approach to computing based on “degrees of truth” rather than the usual “true or false” (1 or 0) boolean logic on which the modern computer is based. Fuzzy logic Systems can take imprecise, distorted, noisy input information.
    • Natural Language Processing: Natural Language Processing (NLP) refers to the Artificial Intelligence method that analyses natural human language to derive useful insights in order to solve problems.

    53) How is Machine Learning related to Artificial Intelligence?

    Ans:

    Artificial Intelligence is a technique that enables machines to mimic human behavior. Whereas, 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.

    Therefore Machine Learning is a technique used to implement Artificial Intelligence.

    Machine Learning-Artificial -Intelligence.

    54) What are the different types of Machine Learning?

    Ans:

    types-Machine-Learning

    55) What is Q-Learning?

    Ans:

    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:

    Q-Learning

    In the above state diagram, the Agent(a0) was in State (s0) and on performing an Action (a0), which resulted in receiving a Reward (r1) and thus being updated to State (s1).

    56) What is Deep Learning?

    Ans:

    Deep learning imitates the way our brain works i.e. it learns from experiences. It uses the concepts of neural networks to solve complex problems.

    Deep-learning

    Any Deep neural network will consist of three types of layers:

    • Input Layer: This layer receives all the inputs and forwards them to the hidden layer for analysis
    • Hidden Layer: In this layer, various computations are carried out and the result is transferred to the output layer. There can be n number of hidden layers, depending on the problem you’re trying to solve.
    • Output Layer: This layer is responsible for transferring information from the neural network to the outside world.

    57) Explain how Deep Learning works.

    Ans:

    • Deep Learning is based on 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 are used to receive inputs.
    • Similarly, a perceptron receives multiple inputs, applies various transformations and functions and provides an output.
    • Just like how our brain contains multiple connected neurons called neural network, we can also have a network of artificial neurons called perceptron’s to form a Deep neural network.
    • An Artificial Neuron or a Perceptron models a neuron which has a set of inputs, each of which is assigned some specific weight. The neuron then computes some function on these weighted inputs and gives the output.

    58) Explain the commonly used Artificial Neural Networks.

    Ans:

    Feedforward Neural Network

    • The 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

    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.

    59) Which is better for image classification? Supervised or unsupervised classification? Justify.

    Ans:

    • In supervised classification, the images are manually fed and interpreted by the Machine Learning expert to create feature classes.
    • In unsupervised classification, the Machine Learning software creates feature classes based on image pixel values.

    Therefore, it is better to choose supervised classification for image classification in terms of accuracy.

    60) Finite difference filters in image processing are very susceptible to noise. To cope up with this, which method can you use so that there would be minimal distortions by noise?

    Ans:

    Image Smoothing is one of the best methods used for reducing noise by forcing pixels to be more like their neighbors, this reduces any distortions caused by contrasts.

    61) How is Game theory and AI related?

    Ans:

    “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.”

    62) What is the Minimax Algorithm? Explain the terminologies involved in a Minimax problem.

    Ans:

    Minimax is a recursive algorithm used to select 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.

    63) Show the working of the Minimax algorithm using Tic-Tac-Toe Game.

    Ans:

    There are two players involved in a game:

    • MAX: This player tries to get the highest possible score
    • MIN: MIN tries to get the lowest possible score

    The following approach is taken for a Tic-Tac-Toe game using the Minimax algorithm:

    • Step 1: First, generate the entire game tree starting with the current position of the game all the way up to the terminal states.
    • 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.

    Let us calculate the utility for the left node(red) of the layer above the terminal:

    MIN{3, 5, 10}, i.e. 3.

    Therefore, the utility for the red node is 3.

    Similarly, for the green node in the same layer:

    MIN{2,2}, i.e. 2.

    • 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

    64) Which method is used for optimizing a Minimax based game?

    Ans:

    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.)

    65) Which algorithm does Facebook use for face verification and how does it work?

    Ans:

    Facebook uses DeepFace for face verification. It works on the face verification algorithm, structured by Artificial Intelligence (AI) techniques using neural network models.

    face-verification

    Here’s how face verification is done:

    Input: Scan a wild form of photos with large complex data. This involves blurry images, images with high intensity and contrast.

    Process: In modern face recognition, the process completes in 4 raw steps:

    • Detect facial features
    • Align and compare the features
    • Represent the key patterns by using 3D graphs
    • Classify the images based on similarity

    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

    66) Explain the logic behind targeted marketing. How can Machine Learning help with this?

    Ans:

    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.

    It is the key to attracting new business, increasing your sales, and growing the company.

    The beauty of target marketing is that by aiming your marketing efforts at specific groups of consumers it makes the promotion, pricing, and distribution of your products and/or services easier and more cost-effective.

    Machine Learning in targeted marketing:

    • Text Analytics Systems: The applications for text analytics ranges from search applications, text classification, named entity recognition, to pattern search and replace applications.
    • Clustering: With applications including customer segmentation, fast search, and visualization.
    • Classification: Like decision trees and neural network classifiers, which can be used for text classification in marketing.
    • Recommender Systems: And association rules which can be used to analyze your marketing data
    • Market Basket Analysis: Market basket analysis explains the combinations of products that frequently
      co-occur in transactions.

    67) How can AI be used in detecting fraud?

    Ans:

    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:

    • Data Extraction: At this stage data is either collected through a survey or web scraping is performed. If you’re trying to detect credit card fraud, then information about the customer is collected. This includes transactional, shopping, personal details, etc.
    • Data Cleaning: At this stage, the redundant data must be removed. Any inconsistencies or missing values may lead to wrongful predictions, therefore such inconsistencies must be dealt with at this step.
    • Data Exploration & Analysis: This is the most important step in AI. Here you study the relationship between various predictor variables. For example, if a person has spent an unusual sum of money on a particular day, the chances of a fraudulent occurrence are very high. Such patterns must be detected and understood at this stage.
    • Building a Machine Learning model: There are many machine learning algorithms that can be used for detecting fraud. One such example is Logistic Regression, which is a classification algorithm. It can be used to classify events into 2 classes, namely, fraudulent and non-fraudulent.
    • Model Evaluation: Here, you basically test the efficiency of the machine learning model. If there is any room for improvement, then parameter tuning is performed. This improves the accuracy of the model.

    68) A bank manager is given a data set containing records of 1000s of applicants who have applied for a loan. How can AI help the manager understand which loans he can approve? Explain.

    Ans:

    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 its neighboring data points.

    The following steps can be carried out to predict whether a loan must be approved or not:

    • Data Extraction: At this stage data is either collected through a survey or web scraping is performed. Data about the customers must be collected. This includes their account balance, credit amount, age, occupation, loan records, etc. By using this data, we can predict whether or not to approve the loan of an applicant.
    • Data Cleaning: At this stage, the redundant variables must be removed. Some of these variables are not essential in predicting the loan of an applicant, for example, variables such as Telephone, Concurrent credits, etc. Such variables must be removed because they will only increase the complexity of the Machine Learning model.
    • Data Exploration & Analysis: This is the most important step in AI. Here you study the relationship between various predictor variables. For example, if a person has a history of unpaid loans, then the chances are that he might not get approval on his loan applicant. Such patterns must be detected and understood at this stage.
    • Building a Machine Learning model: There are n number of machine learning algorithms that can be used for predicting whether an applicant loan request is approved or not. One such example is the K-Nearest Neighbor, which is a classification and a regression algorithm. It will classify the applicant’s loan request into two classes, namely, Approved and Disapproved.
    • Model Evaluation: Here, you basically test the efficiency of the machine learning model. If there is any room for improvement, then parameter tuning is performed. This improves the accuracy of the model.

    69) You’ve won a 2-million-dollar worth lottery’ we all get such spam messages. How can AI be used to detect and filter out such spam messages?

    Ans:

    To understand spam detection, let’s take the example of Gmail. 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:

    • A machine learning process always begins with data collection. We all know the data Google has, is not obviously in paper files. They have data centers which maintain the customer’s data. Data such as email content, header, sender, etc are stored.
    • This is followed by data cleaning. It is essential to get rid of unnecessary stop words and punctuations so that only the relevant data is used for creating a precise machine learning model. Therefore, in this stage stop words such as ‘the’, ‘and’, ‘a’ are removed. The text is formatted in such a way that it can be analyzed.
    • After data cleaning comes data exploration and analysis. Many times, certain words or phrases are frequently used in spam emails. Words like “lottery”, “earn”, “full-refund” indicate that the email is more likely to be a spam one. Such words and co-relations must be understood in this stage.
    • After retrieving useful insights from data, a machine learning model is built. For classifying emails as either spam or non-spam you can use machine learning algorithms like Logistic Regression, Naïve Bayes, etc. The machine learning model is built using the training dataset. This data is used to train the model and make it learn by using past user email data.
    • This stage is followed by model evaluation. In this phase, the model is tested using the testing data set, which is nothing but a new set of emails. After which the machine learning model is graded based on the accuracy with which it was able to classify the emails correctly.
    • Once the evaluation is over, any further improvement in the model can be achieved by tuning a few variables/parameters. This stage is also known as parameter tuning. Here, you basically try to improve the efficiency of the machine learning model by tweaking a few parameters that you used to build the model.
    • The last stage is deployment. Here the model is deployed to the end users, where it processes emails in real time and predicts whether the email is spam or non-spam.

    70) Let’s say that you started an online shopping business and to grow your business, you want to forecast the sales for the upcoming months. How would you do this? Explain.

    Ans:

    This can be done by studying the past data and building a model that shows how the sales have varied over a period of time. Sales Forecasting is one of the most common applications of AI. Linear Regression is one of the best Machine Learning algorithms used for forecasting sales.

    When both sales and time have a linear relationship, it is best to use a simple linear regression model.

    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.

    • Dependent variable (Y):
      The response variable whose value needs to be predicted.
    • Independent variable (X):
      The predictor variable used to predict the response variable.

    In this example, the dependent variable ‘Y’ represents the sales and the independent variable ‘X’ represents the time period. Since the sales vary over a period of time, sales is the dependent variable.

    The following equation is used to represent a linear regression model:

    Y=??+?? ?+ⅇ

    Here,

    • Y = Dependent variable
    • ?? = Y-Intercept
    • ?? = Slope of the line
    • x = Independent variable
    • e = Error

    Therefore, by using the Linear Regression model, wherein Y-axis represents the sales and X-axis denotes the time period, we can easily predict the sales for the upcoming months.

    Artificial Intelligence Sample Resumes! Download & Edit, Get Noticed by Top Employers! Download

    71) ‘Customers who bought this also bought this…’ we often see this when we shop on Amazon. What is the logic behind recommendation engines?

    Ans:

    • E-commerce websites like Amazon make use of Machine Learning to recommend products to their customers. The basic idea of this kind of recommendation comes from collaborative filtering. Collaborative filtering is the process of comparing users with similar shopping behaviors in order to recommend products to a new user with similar shopping behavior.
    • To better understand this, let’s look at an example. Let’s say a user A who is a sports enthusiast bought pizza, pasta, and a coke. Now a couple of weeks later, another user B who rides a bicycle buys pizza and pasta. He does not buy the coke, but Amazon recommends a bottle of coke to user B since his shopping behaviors and his lifestyle is quite similar to user A. This is how collaborative filtering works.

    72) What is market basket analysis and how can Artificial Intelligence be used to perform this?

    Ans:

    Market basket analysis explains the combinations of products that frequently co-occur in transactions.

    For example, if a person buys bread, there is a 40% chance that he might also buy butter. By understanding such correlations between items, companies can grow their businesses by giving relevant offers and discount codes on such items.

    Market Basket Analysis is a well-known practice that is followed by almost every huge retailer in the market. The logic behind this is Machine Learning algorithms such as Association Rule Mining and Apriori algorithm:

    • Association rule mining is a technique that shows how items are associated with each other.
    • Apriori algorithm uses frequent itemsets to generate association rules. It is based on the concept that a subset of a frequent itemset must also be a frequent itemset.

    For example, the above rule suggests that, if a person buys item A then he will also buy item B. In this manner the retailer can give a discount offer which states that on purchasing Item A and B, there will be a 30% off on item C. Such rules are generated using Machine Learning. These are then applied on items in order to increase sales and grow a business.

    73) Place an agent in any one of the rooms (0,1,2,3,4) and the goal is to reach outside the building (room 5). Can this be achieved through AI? If yes, explain how it can be done.

    Ans:

    In the above figure:

    • 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 into the building from room 5 (outside)

    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, like so:

    Q-Learning-algorithm

    Next step is to associate a reward value to each door:

    Q-Learning-algorithms
    • 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

    Now let’s try to understand how Q-Learning can be used to solve this problem. The terminology in Q-Learning includes the terms state and action:

    • The 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. Suppose, the Agent traverses from room 2 to room5, then the following path is taken:

    • Initial state = state 2
    • State 2 -> state 3
    • State 3 -> state (2, 1, 4)
    • State 4 -> state 5

    Next, we can put the state diagram and the instant reward values into a reward table or a matrix R, like so:

    Q-Learning-algorithm-reward-table

    The next step is to 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

    The formula to calculate the Q matrix:

    Q(state, action) = R(state, action) + Gamma * Max [Q(next state, all actions)]

    Here, Q(state, action) and R(state, action) represent the state and action in the Reward matrix R and the Memory matrix Q.

    Note: 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

    Finally, by following the below steps, the agent will reach room 5 by taking the most optimal path:

    Gamma-parameter

    74) The crop yield in India is degrading because farmers are unable to detect diseases in crops during the early stages. Can AI be used for disease detection in crops? If yes, explain.

    Ans:

    AI can be used to implement image processing and classification techniques for extraction and classification of leaf diseases.

    This sounds complex, let me break it down into steps:

    Image Acquisition: The sample images are collected and stored as an input database.

    Image Pre-processing: Image pre-processing includes the following:

    • Improve image data that suppresses unwanted distortion
    • Enhance image features
    • Image clipping, enhancement, color space conversion
    • Perform Histogram equalization to adjust the contrast of an image

    Image Segmentation: It is the process of partitioning a digital image into multiple segments so that image analysis becomes easier.  Segmentation is based on image features such as color, texture. A popular Machine Learning method used for segmentation is the K-means clustering algorithm.

    Feature Extraction: This is done to extract information that can be used to find the significance of a given sample. The Haar Wavelet transform can be used for texture analysis and the computations can be done by using Gray-Level Co-Occurrence Matrix.

    Classification: Finally, Linear Support Vector Machine is used for classification of leaf disease. SVM is a binary classifier which uses a hyperplane called the decision boundary between two classes. This results in the formation of two classes:

    • Diseased leaves
    • Healthy leaves

    Therefore, AI can be used in Computer Vision to classify and detect disease by studying and processing images. This is one of the most profound applications of AI.

    75) What’s an eigenvalue? What about an eigenvector?

    Ans:

    The directions along which a particular linear transformation compresses, flips, or stretches is called eigenvalue. Eigenvectors are used to understand these linear transformations.

    For example, to make better sense of the covariance of the covariance matrix, the eigenvector will help identify the direction in which the covariances are going. The eigenvalues will express the importance of each feature.

    Eigenvalues and eigenvectors are both critical to computer vision and ML applications. The most popular of these is known as principal component analysis for dimensionality reduction (e.g., eigenfaces for face recognition).

    76) Would you use batch normalization? If so, can you explain why?

    Ans:

    The idea here is to standardize the data before sending it to another layer. This approach helps reduce the impact of previous layers by keeping the mean and variance constant. It also makes the layers independent of each other to achieve rapid convergence. For example, when we normalize features from 0 to 1 or from 1 to 100, it helps accelerate the learning cycle.

    77) What’s a hash table?

    Ans:

    There are two parts to a hash table. The first is an array, or the actual table where the data is stored, and the other is a mapping function that’s known as the hash function.

    It’s a data structure that implements an associative array abstract data type that can map key values. It can also compute an index into an array of slots or buckets where the desired value can be found.

    78) What are the different algorithm techniques you can use in AI and ML?

    Ans:

    Some algorithm techniques that can be leveraged are:

    • Learning to learn
    • Reinforcement learning (deep adversarial networks, q-learning, and temporal difference)
    • Semi-supervised learning
    • Supervised learning (decision trees, linear regression, naive bayes, nearest neighbor, neural networks, and support vector machines)
    • Transduction
    • Unsupervised learning (association rules and k-means clustering)

    79) How would you go about choosing an algorithm to solve a business problem?

    Ans:

    First, you have to develop a “problem statement” that’s based on the problem provided by the business. This step is essential because it’ll help ensure that you fully understand the type of problem and the input and the output of the problem you want to solve.

    The problem statement should be simple and no more than a single sentence. For example, let’s consider enterprise spam that requires an algorithm to identify it.

    The problem statement would be: “Is the email fake/spam or not?” In this scenario, the identification of whether it’s fake/spam will be the output.

    Once you have defined the problem statement, you have to identify the appropriate algorithm from the following:

    • Any classification algorithm
    • Any clustering algorithm
    • Any regression algorithm
    • Any recommendation algorithm

    Which algorithm you use will depend on the specific problem you’re trying to solve. In this scenario, you can move forward with a clustering algorithm and choose a k-means algorithm to achieve your goal of filtering spam from the email system.

    80) When is it necessary to update an algorithm?

    Ans:

    You should update an algorithm when the underlying data source has been changed or whenever there’s a case of non-stationarity. The algorithm should also be updated when you want the model to evolve as data streams through the infrastructure.

    81) What’s regularization?

    Ans:

    When you have underfitting or overfitting issues in a statistical model, you can use the regularization technique to resolve it. Regularization techniques like LASSO help penalize some model parameters if they are likely to lead to overfitting.

    82) What’s the difference between inductive, deductive, and abductive learning?

    Ans:

    Inductive learning describes smart algorithms that learn from a set of instances to draw conclusions. In statistical ML, k-nearest neighbor and support vector machine are good examples of inductive learning.

    There are three literals in (top-down) inductive learning:

    • Arithmetic literals
    • Equality and inequality
    • Predicates

    In deductive learning, the smart algorithms draw conclusions by following a truth-generating structure (major premise, minor premise, and conclusion) and then improve them based on previous decisions. In this scenario, the ML algorithm engages in deductive reasoning using a decision tree.

    Abductive learning is a DL technique where conclusions are made based on various instances. With this approach, inductive reasoning is applied to causal relationships in deep neural networks.

    83) What steps would you take to evaluate the effectiveness of your ML model?

    Ans:

    You have to first split the data set into training and test sets. You also have the option of using a cross-validation technique to further segment the data set into a composite of training and test sets within the data.

    Then you have to implement a choice selection of the performance metrics like the following:

    • Confusion matrix
    • Accuracy
    • Precision
    • Recall or sensitivity
    • Specificity
    • F1 score

    84) What would you do if data in a data set were missing or corrupted?

    Ans:

    Whenever data is missing or corrupted, you either replace it with another value or drop those rows and columns altogether. In Pandas, both isNull() and dropNA() are handy tools to find missing or corrupted data and drop those values. You can also use the fillna() method to fill the invalid values in a placeholder—for example, “0.”

    85) Define Automation and Robotics

    Ans:

    The purpose of Automation is to get the monotonous and repetitive tasks done by machines which also improve productivity and in receiving cost-effective and more efficient results. Many organizations use machine learning, neural networks, and graphs in automation. Such automation can prevent fraud issues while financial transactions online by using CAPTCHA technology. Robotic process automation is programmed to perform high volume repetitive tasks which can adapt to the change in different circumstances.

    86) Which domain study Artificial Included?

    Ans:

    • Computer Science
    • Cognitive Science
    • Engineering
    • Ethics
    • Linguistics
    • Logic
    • Mathematics
    • Natural Sciences
    • Philosophy
    • Physiology
    • Psychology
    • Statistics

    87) What is the philosophy behind Artificial Intelligence?

    Ans:

    As if we see the powers that are exploiting the power of the computer system, the curiosity of humans lead him to wonder, “Can a machine think and behave like humans do?” Thus, AI was started with the intention of creating similar intelligence in machines. Also, that we find and regard high in humans.

    88) Explain Goal of Artificial Intelligence?

    Ans:

    To Create Expert Systems it is the type of system in which the system exhibits intelligent behavior, and advises its users. b. To Implement Human Intelligence in Machines It is the way of creating the systems that understand, think, learn, and behave like humans.

    89) What contributes to Artificial Intelligence?

    Ans:

    Basically, artificial intelligence relates to following disciplines such as –

    • Computer Science
    • Biology
    • Psychology
    • Linguistics
    • Mathematics and
    • Engineering

    90) Name types of Artificial Intelligence?

    Ans:

    • Strong artificial intelligence
    • Weak artificial intelligence

    91) Explain types of Artificial Intelligence?

    Ans:

    There are two types of artificial intelligence such as:

    • Strong artificial intelligence

    Basically, it deals with the creation of real intelligence artificially. Also, strong AI believes that machines can be made sentient.

    There are two types of strong AI: Human-like AI In this computer program thinks and reasons to the level of human-being. Non-human-like AI In this computer program develops a non-human way of thinking and reasoning.

    • Weak artificial intelligence

    As a result, it doesn’t believe creating human-level intelligence in machines is possible. Although, AI techniques can be developed to solve many real-life problems.

    92) Why is A.I needed?

    Ans:

    There are some reasons behind its need. So, let us first compare differences between traditional Computer programs vs. Human Intelligence. As it’s identified that normal humans have the same intellectual mechanisms. Moreover, the difference in intelligence is related to “quantitative biochemical and physiological conditions.” Traditionally, we use computing for performing mechanical computations using fixed procedures. Also, there are more complex problems which we need to solve.

    93) What is AI technique?

    Ans:

    Basically, its volume is huge, next to unimaginable. Although, it keeps changing constantly. As AI Technique is a manner to organize. Also, we use it efficiently in such a way that − Basically, it should be perceivable by the people who provide it. As it should be easily modifiable to correct errors. Moreover, it should be useful in many situations. Though it is incomplete or inaccurate.

    94) Give some advantages to Artificial Intelligence?

    Ans:

    • Error Reduction

    We use artificial intelligence in most of the cases. As this helps us in reducing the risk. Also, increases the chance of reaching accuracy with the greater degree of precision.

    • Difficult Exploration

    In mining, we use artificial intelligence and science of robotics. Also, other fuel exploration processes. Moreover, we use complex machines for exploring the ocean. Hence, overcoming the ocean limitation.

    • Daily Application

    As we know that computed methods and learning have become commonplace in daily life. Financial institutions and banking institutions are widely using AI. That is to organize and manage data. Also, AI is used in the detection of fraud users in a smart card based system.

    95) Give some disadvantages of Artificial Intelligence?

    Ans:

    High Cost Its creation requires huge costs as they are very complex machines. Also, repair and maintenance require huge costs.

    No Replicating Humans As intelligence is believed to be a gift of nature. An ethical argument continues, whether human intelligence is to be replicated or not.

    Lesser Jobs As we are aware that machines do routine and repeatable tasks much better than humans. Moreover, we use machines instead of humans. As to increase their profitability in businesses.

    Lack of Personal Connections We can’t rely too much on these machines for educational oversights. That hurt learners more than help.

    96) Explain artificial intelligence examples and applications?

    Ans:

    • Virtual Personal Assistants

    Basically, it is processed in which we have to collect a huge amount of data. That is collected from a variety of sources to learn about users. Also, one needs to be more effective in helping them organize and track their information. For Example There are various platforms like iOS, Android, and Windows mobile. We use intelligent digital personal assistants like Siri, Google Now, and Cortana. AI plays an important role in this apps. If you demand they use it to collect the information. And this information is used to recognize your request and serves your result.

    • Smart Cars

    There are two examples: That feature Google’s self-driving car project and Tesla’s “autopilot”. Also. artificial intelligence has been used since the invention of the first video game.

    • Prediction

    We call it the use of predictive analytics. Its main purpose is potential privacy. Also, we can use it in many ways. As it’s also sending you coupons, offering you discounts. That is close to your home with products that you will like to buy. Further, we can call it the controversial use of artificial intelligence.

    • Fraud Detection

    We use AI to detect fraud. As many frauds always happen in banks. Also, computers have a large sample of fraudulent and non-fraudulent purchases. As they asked to look for signs that a transaction falls into one category or another.

    97) What are Educational Requirements for Career in Artificial Intelligence?

    Ans:

    • Various levels of math, including probability, statistics, algebra, calculus, logic, and algorithms.
    • Bayesian networking or graphical modeling, including neural nets.
    • Physics, engineering, and robotics.
    • Computer science, programming languages, and coding.
    • Cognitive science theory.

    98) What are artificial intelligence career domains?

    Ans:

    A career in this can be realized within a variety of settings including : private companies public organizations education the arts healthcare facilities government agencies and the military.

    99) What are roles in an AI career?

    Ans:

    • Software analysts and developers.
    • Computer scientists and computer engineers.
    • Algorithm specialists.
    • Research scientists and engineering consultants.
    • Mechanical engineers and maintenance technicians.
    • Manufacturing and electrical engineers.
    • Surgical technicians working with robotic tools.
    • Military and aviation electricians working with flight simulators, drones, and armaments.

    100) What is the future of Artificial intelligence?

    Ans:

    Artificial Intelligence is used by one another after the company for its benefits. Also, it’s a fact that artificial intelligence is reached in our day-to-day life. Moreover, with a breakneck speed. On the basis of this information, arises a new question: Is it possible that artificial Intelligence outperforms human performance? If yes, then does it happen and how much does it take? Only when Artificial Intelligence is able to do a job better than humans.

    Are you looking training with Right Jobs?

    Contact Us
    Get Training Quote for Free