Artificial Intelligence Interview Questions and Answers in 2022

Artificial Intelligence (AI) is a sub-field of Computer Science dedicated to solving cognitive issues normally associated with human intelligence which include learning, recognition and Problem fixing.AI is unexpectedly remodelling our global with innovations like self-sustaining motors driving our metropolis streets, non-public or personal digital assistants in our homes and pockets, and direct human brain interfaces which can assist a paralyzed character experience again whilst using a mind-controlled robotic arm and more

The term artificial intelligence is also used to describe an asset of machines or programs: the intelligence that the device demonstrates. AI studies makes use of equipment and insights from many fields, including computer technology, philosophy, psychology, neuroscience, cognitive science, linguistics, operations research, economics, manage principle, possibility, optimization and logic.AI research additionally overlaps with responsibilities such as robotics, manage structures, scheduling, information mining, logistics, speech popularity, facial recognition and more different fields.

Here are some of the important programming languages

• R
• Python
• Lisp
• Java
• ProLog
• Smalltalk

Other programming languages are:

• MATLab
• Julia
• C++
• POP-11
• IPL
• AIML
• Haskell
• Perl

• Robotics
• Neural networks
• Vision Systems
• Expert systems
• Learning systems
• Natural language processing
• Logical AI
• Search
• Inference
• Pattern recognition
• Representations
• Planning
• Data mining
• Statistical AI
• Fuzzy logic
• Genetic algorithm
• Ontology
• Epistemology
• Heuristics

Expert system is a computer program that uses artificial-intelligence methods to solve problems within a specialized domain that ordinarily requires human expertise. Typical tasks for expert systems involve classification, diagnosis, monitoring, and design, scheduling, and planning for specialized endeavours.

Short History of Expert Systems

The first expert system was developed in 1965 by Edward Feigenbaum and Joshua Lederberg of Stanford University in California, U.S. Dendral, as their expert system was later known, was designed to analyze chemical compounds. Expert systems now have commercial applications in fields as diverse as medical diagnosis, petroleum engineering, and financial investing.

The components of Expert Systems are

Primary Components are

• Knowledge base
• Interface Engine
• User Interface

Other components

• Working Memory
• Knowledge Acquisition Subsystem
• Explanation module
• Development Engine

A knowledge base is an organized collection of facts about the system’s domain. The knowledge base of Expert systems contains both factual and heuristic knowledge. Knowledge representation is the method used to organize the knowledge in the knowledge base. Knowledge bases must represent notions as actions to be taken under circumstances, causality, time, dependencies, goals, and other higher-level concepts.

There are two types of Knowledge base Components

Factual Knowledge: knowledge Engineers and Scholar used this in the task domain.

Heuristic Knowledge: we can say it’s all about practice, accurate judgment and one’s ability of evaluation.

Interference engine is also known as the control structure or the rule interpreter. An inference engine interprets and evaluates the facts in the knowledge base in order to provide an answer. It performs this task in order to deduce new facts which are subsequently used to draw further conclusions. The interference engine is the active component of an expert system. It is the Brain of the expert system.

An expert system can use two different methods of inferencing

Backward Chaining System (a goal driven system): It’s works with the system assuming a hypothesis of what the likely outcome will be, and the system then works backwards to collect the evidence that would support this conclusion. Expert systems used for planning often use backward chaining.

Forward Chaining expert system (a data driven system): It is simply gathers facts (like a detective at the scene of a crime) until enough evidence is collected that points to an outcome. Forward chaining is often used in expert systems for diagnosis, advice and classification, although the size and complexity of the system can play a part in deciding which method of inferencing to use.

It enables the users to enter instruction and information into the expert system and to receive information from it. The information is in the form of values assigned to certain variables. The user interface has two parts:

Expert System Input: A user can use method for input command, natural language and customize the interface.

Expert System Output: Expert systems are designed to provide output or solution for a specific domain.

The process of capturing and transformation of potentially useful information for given problems from any knowledge source (this may be a human expert) to a program in the format required by that program is the job of a knowledge acquisition subsystem. So we can say that these subsystem to help experts build knowledge base.  Or Knowledge Acquisition program is used by an individual, who has expertise in the problem to, creates, add to or change the knowledge base. Potential sources of knowledge include human expert, research reports, textbooks, databases and the user’s own experience

Development engine is used to create the expert system. This process usually involved building the rule set. There are two basic approaches-

Programming Language: An expert system can be created using any programming language. However, two especially suited to the symbolical representation of knowledge is LISP and Prolog.

Expert System Shell: Expert system shell is a readymade processor that can be tailored to specific problem domain through the addition of the appropriate knowledge base. In most cases, the shell can be produced an expert system quicker and easier than by programming language. The first commercial shell was for knowledge engineering environment (K.E.E.). It was designed for the use of a computer design, especially for LISP language for a LISP machine.

Working Memory is a database used to store collection of facts which will later be used by the rules. More effort may go into the design and implementation of the user interface than in the expert system knowledge base. Working memory is used by the inference engine to get facts and match them against the rules. The facts may be added to the working memory by applying some rules

Explanation module helps the expert system to give the user an explanation about how the expert system reached a particular conclusion.

Availability: Due to mass production of software, expert systems are easily available.

Less Production Cost: As the production cost of an expert system is reasonable. Thus, it makes them affordable.

High Speed: Expert systems offer great speed. Also, reduce the amount of work that an individual puts in.

Less Error Rate: Generally, an error rate of the expert system is low in comparison to human errors.

Reduced danger: They can be used in any risky environments where humans cannot work with.

Permanence: The knowledge will last long indefinitely.

Multiple expertises: It can be designed to have knowledge of many experts.

Explanation: They are capable of explaining in detail the reasoning that led to a conclusion.

Fuzzy logic is a method of reasoning that resembles human reasoning since it allows for approximate values and inferences and incomplete or ambiguous data (fuzzy data). Fuzzy logic is a method of choice for handling uncertainty in some expert systems. Expert systems with fuzzy-logic capabilities thus allow for more flexible and creative handling of problems. These systems are used, for example, to control manufacturing processes.

A rule-based expert system is the simplest form of artificial intelligence and uses prescribed knowledge-based rules to solve a problem 1.  The aim of the expert system is to take knowledge from a human expert and convert this into a number of hardcoded rules to apply to the input data. In their most basic form, the rules are commonly conditional statements (if a, then do x, else if b, then do y). These systems should be applied to smaller problems, as the more complex a system is, the more rules that are required to describe it, and thus increased difficulty to model for all possible outcomes.

The term rule in Artificial intelligence, which is the most commonly used type of knowledge representation, can be defined as an IF-THEN structure that relates given information or facts in the IF part to some action in the THEN part. ß A rule provides some description of how to solve a problem.

• Rule is relatively easy to create and understand
• Any rules consist of two parts: the IF part, called the antecedent (premise or condition) and the THEN part called the consequent (conclusion or action) IF THEN
• A rule can have multiple antecedents joined by the keywords AND (conjunction), OR (disjunction) or a combination of both.
• The antecedent of a rule incorporates two parts: an object (linguistic object) and its value. The object and its value are linked by an operator.
• The operator identifies the object and assigns the value. Operators such as is, are, is not, are not are used to assign a symbolic value to a linguistic object.
• Rules can represent

Relation:

IF the ‘fuel tank’ is empty T

HEN the car is dead •

Recommendation:

IF the season is autumn

AND the sky is cloudy

AND the forecast is drizzle

THEN the advice is ‘take an umbrella’ •

Directive:

IF the car is dead

AND the ‘fuel tank’ is empty

THEN the action is ‘refuel the car’ B219 Intelligent Systems.

Strategy:

IF the car is dead THEN the action is ‘check the fuel tank’; step1 complete IF step1 is complete AND the ‘fuel tank’ is full THEN the action is ‘check the battery’; step2 is complete •

Heuristic:

IF the spill is liquid AND the ‘spill pH’ < 6 AND the ‘spill smell’ is vinegar THEN the ‘spill material’ is ‘acetic acid.

• Expert system has no emotions.
• Common sense is the main issue of the expert system.
• It is developed for a specific domain.
• It needs to be updated manually. It does not learn itself.
• Not capable to explain the logic behind the decision.

FOPL stands for First-order Predicate logic, which is a congregation of formal systems, with the statement being divided into two parts: a predicate and a subject. The predicate holds the potential to define or modify the subject’s properties.

CSPs (Constraint Satisfaction Problems) are mathematical problems defined as a set of objects the state of which must meet a number of constraints. CSPs are useful for AI because the regularity of their formulation offers a commonality for analyzing and solving problems.

Agent: Like, anything that perceives its environment by the sensors, and act upon an environment by effectors are called as Agent. E.g. Robots, Programs, Humans, HCI, HMI etc.

Partial Order or Planning: Instead of searching over possible situation that involves searching over the space of possible plans. Then the idea can be constructing as a plan piece by piece.

Statistical AI, arising from machine learning, tends to be more concerned with “inductive” thought: given a set of patterns, induce the trend. Classical AI, on the other hand, is more concerned with “deductive” thought: given a set of constraints, deduce a conclusion. Another difference, as mentioned in the previous question, is that C++ tends to be a favourite language for statistical AI while LISP dominates in classical AI.

A system can’t be truly intelligent without displaying properties of both inductive and deductive thought. This lends many to believe that in the end, there will be some kind of synthesis of statistical and classical AI. 

Alternate Key: Alternate Keys is excluding primary keys of all candidate keys.

Artificial Key: Artificial key is when no obvious key either stands alone or a compound is available. This leaves it with no option other than to create a key, which it does by assigning a number to each record or occurrence.

Compound Key: Integrating multiple elements to create a unique identifier for the construct becomes necessary when no single data element that uniquely defines the occurrence within a construct is available. This is known as Compound Key.

Natural Key: One of the data elements stored within a construct is a Natural Key. It is utilized as the primary key.

Learning Rate: Learning rate is how fast the network learns new beliefs.

Momentum: Parameter which helps to come out of local minima and smoothen the jumps while gradient decent.

Epoch: Epoch is the complete once forward and backward propagation to correct its weights. As epoch increases loss or error decreases as it learns better and better.

.

Relational knowledge representation scheme in which facts are represented as a set of relations. For example knowledge about players can be represented using a relation called “player” having three fields: player name, height and weight. This form of knowledge representation provides weak inferential capabilities when used as standalone but are useful as an input for sophisticated inferential procedures.

This knowledge representation scheme in which knowledge is represented using objects, their attributes and corresponding value of the attributes. The relation between different objects is defined using a “isa” property. For example if two entities “Adult male” and “Person” are represented as objects then the relation between the two is that Adult male “isa” person.

• Sigmoid Function
• Linear Function
• Hyperbolic Tangent
• ReLU(Rectified Linear Unit)
• Leaky ReLU
• Tanh Function
• Stochastic Binary function
• Binary Threshold Function

In artificial intelligence, 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

It is a test performed to determine a machine’s ability to exhibit intelligent behaviour. The basic concept behind the test is that if a human judge is engaged in a natural language conversation with a computer where he cannot reliably distinguish machine from human, the machine passes the test. Turing test, in artificial intelligence, a test proposed (1950) by the English mathematician Alan M. Turing to determine whether a computer can “think.”

Alpha-beta pruning is a procedure to reduce the amount of computation and searching during minimax. Minimax is a two-pass search, one pass is used to assign heuristic values to the nodes at the ply depth and the second is used to propagate the values up the tree.

Tower of Hanoi consists of three pegs or towers with n disks placed one over the other. The objective of the puzzle is to move the stack to another peg following these simple rules.

• Only one disk can be moved at a time.
• No disk can be placed on top of the smaller disk.
• Before we proceed, let’s understand Recursion –

Greedy Best First Search algorithm process where the node closest to the goal will be expanded first. The default explanation of nodes goes by f(n) = h(n). This technique is applied at a later stage, where priority queue will come into the picture.

Start with the root node, then proceed through neighboring nodes. Further, moves towards next level of nodes. Till the arrangement is found, produces one tree at any given moment. As this pursuit can be executed utilizing FIFO(First in First Out) data structure. This strategy gives the shortest path to the solution.

Ensemble learning is a computational technique in which classifiers or experts are strategically formed and combined. It is used to improve the classification, prediction, and function approximation etc of a model.

When a function calls itself, it’s called Recursion. It will be easier for those who have seen the movie Inception. Leonardo had a dream, in that dream he had another dream, in that dream he had yet another dream and that goes on. So it’s like there is a function called dream ()dream(), and we are just calling it in itself.

The repetitive search process of level 1, level 2 happens in this search. The search process continues till the solution is found. Nodes are generated till a single node is created. Stack of nodes are saved. The search ends once the solution is found.

A* is a computer algorithm that is extensively used for the purpose of finding the path or traversing a graph in order to find the most optimal route between the various points called as the nodes.

Depth first search is based on LIFO (Last In First Out). A recursion is implemented with LIFO stack data structure. Thus, the nodes were different order than in BFS. The path is stored in each iteration from root to leaf node in linear with space requirement.

The search begins forward from the beginning state and in reverse from objective state. The search meets to identify a common state. The initial state way is linked with the objective state in reverse way. Each search is done just up to half of the aggregate way.

The uniform cost search performs sorting in increasing cost of the path to a node. It expands the least cost node. It is identical to BFS if each iteration has same cost. It investigates ways in the expanding order of cost.

Machine learning and deep learning fall under the topic of artificial intelligence. Machine learning describes a process of computers acquiring knowledge on their own. Deep learning has become the most common method of machine learning: This involves a computer acquiring its knowledge using an algorithm, which is used to analyze large volumes of data, and learning to draw conclusions based on this data. Here’s a simple example: Let’s say we want a system’s algorithm to learn how to identify stop signs. We show it one million pictures of stop signs; it accumulates experience as a result. On this basis, the system is subsequently able to identify a stop sign when it appears.

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

An Agent is anything that can be viewed as perceiving its environment through sensors and acting upon that environment through actuators.