AJAY KUMAR GARG ENGINEERING COLLEGE, GHAZIABAD

INTERVIEW BASED QUESTIONS

ARTIFICIAL INTELLIGENCE (KCS-071)

Q1. What are the different types of AI?

There are two main types of AI: narrow AI and general AI. Narrow AI is designed to perform a
specific task, while general AI is capable of performing any intellectual task that a human being
can.

Q2 What are the benefits of AI?

AI has the potential to revolutionize many aspects of our lives, including healthcare,
transportation, education, and manufacturing. It can help us to solve some of the world's biggest
problems, such as climate change and poverty.

Q3. What are the risks of AI?

There are also risks associated with AI, such as the potential for job displacement, bias, and
security breaches. It is important to develop ethical guidelines for the development and use of AI
to mitigate these risks.

Q4. How is AI used in the real world?

AI is already being used in a variety of ways in the real world, including:

● Self-driving cars
● Facial recognition
● Natural language processing
● Machine translation
● Predictive analytics
● Robotics

Q5. What are the ethical implications of AI?

The ethical implications of AI are complex and still being debated. Some of the key ethical
issues include:
 ● Privacy
● Bias
● Accountability, Safety

Q6. What are the challenges of AI?

There are a number of challenges associated with AI, including:

● The need for large amounts of data
● The difficulty of understanding and interpreting AI models
● The potential for bias and discrimination
● The risk of job displacement

Q7. What are the future trends in AI?

Some of the key future trends in AI include:

● The development of more powerful AI algorithms
● The increasing use of AI in healthcare, transportation, education, and manufacturing
● The development of ethical guidelines for the development and use of AI

Q8. What is the Turing Test, and why is it important?

The Turing Test, proposed by Alan Turing in his 1950 paper "Computing Machinery and
Intelligence," is a method to determine whether a machine exhibits intelligent behavior
indistinguishable from that of a human. The test involves a conversation between three
participants:
1. A human interrogator.
2. A human respondent.
3. A machine respondent (the AI being tested).
The interrogator communicates with the respondents via a text interface (to remove visual or
auditory biases) and must determine which is the human and which is the machine. If the
interrogator cannot reliably distinguish the machine from the human, the machine is said to have
passed the Turing Test.

The Turing Test is significant as it provides an early benchmark for artificial intelligence,
particularly in natural language processing and human-computer interaction

Q9. Can you explain the difference between AI, Machine Learning, and Deep Learning?
AI is a broad field focused on creating intelligent machines. Machine Learning is a subset of AI
that includes techniques that allow machines to improve at tasks with experience. Deep Learning
is a subset of ML that uses neural networks with many layers (deep networks) to learn from large
amounts of data. Deep Learning is especially effective for tasks involving image recognition,
speech recognition, and natural language processing.

Q10.What is a Rational Agent, and What is Rationality?

A rational agent is an entity (such as a human, robot, or software program) that perceives its
environment through sensors and acts upon it using actuators to achieve specific goals. Its
actions are guided by a rational decision-making process that aims to maximize its performance
measure based on available knowledge and evidence. In the context of artificial intelligence,
rational agents are designed to operate effectively in a variety of environments, often adapting to
changes and uncertainties.

Rationality refers to the quality of making decisions and taking actions that are expected to
maximize the agent's performance measure, given the information available. It involves:

1. Performance Criteria: The objective or goal the agent aims to achieve.

2. Perceptual Information: The observations and knowledge about the environment.
3. Actions: Choices made by the agent to achieve its goal.
4. Outcome Evaluation: Assessing actions based on their success in achieving the desired
outcomes.

Rationality is not perfection; it considers the limitations of knowledge, computational power, and
environmental uncertainty, aiming for the best possible action under given circumstances.

Q11. Can you give an example of how AI has transformed a traditional industry?

AI has revolutionized the retail industry by enhancing customer experience, optimizing

operations, and driving sales.

One transformative application is the use of AI-powered recommendation systems. Retail

giants like Amazon and Netflix leverage machine learning algorithms to analyze customer
behavior, purchase history, and preferences. These systems provide personalized product
suggestions, boosting customer satisfaction and significantly increasing sales. For example,
Amazon's recommendation engine accounts for a substantial portion of its revenue by suggesting
complementary or related items to customers.
Another major innovation is AI-driven inventory management and demand forecasting.
Traditional retail often struggled with overstocking or stockouts due to inaccurate demand
predictions. AI systems now analyze historical sales data, seasonal trends, and external factors
like weather or events to optimize inventory levels. Walmart, for instance, uses AI to forecast
demand and ensure products are available when and where customers need them, reducing waste
and improving efficiency.

Additionally, AI chatbots and virtual assistants enhance customer service by handling queries,
tracking orders, and providing instant support, creating seamless shopping experiences. Retailers
like H&M and Sephora use AI-driven chatbots to recommend outfits or beauty products tailored
to customer preferences.

These applications showcase how AI has modernized retail, making it more customer-centric,
efficient, and profitable.

Q12. What is the significance of the A* algorithm in AI?

The A* algorithm is significant in AI for its efficiency and effectiveness in pathfinding and graph
traversal. It uses heuristics to estimate the cost to reach the goal from each node, optimizing the
search process for the shortest path. It is widely used in applications like game development,
robotics, GPS navigation, and AI planning, A* adapts to various challenges with modifications
such as weighted or memory-efficient versions. Its ability to integrate problem-specific heuristics
while maintaining efficiency makes it a fundamental tool for pathfinding and graph traversal in
AI.

Q13. Explain the Hidden Markov Model.

A Hidden Markov Model (HMM) is a statistical model that represents a system as a Markov
process with hidden states. It is widely used in fields like natural language processing, speech
recognition, bioinformatics, and more.
HMM consists of two types of variables:
1. Hidden states (unobservable):

○ Represent the actual states of the system, which are not directly visible.
○ Example: Emotional state (Happy, Sad, Neutral) in speech recognition.
2. Observations (observable):
○ These are the visible outcomes generated by the hidden states.
○ Example: The actual speech audio features observed.

The basic idea behind an HMM is that there is a sequence of hidden states that are not directly
observable, but generate a sequence of observations. Each hidden state has a probability
distribution over the possible observations, and the sequence of hidden states changes over time
according to certain probability transition rule.

Q14. Difference between strong and weak AI

Strong AI (Artificial General Intelligence): Refers to machines with the ability to apply
intelligence to any problem, rather than just specific ones. Strong AI systems can perform any
intellectual task that a human can.

Weak AI (Narrow AI): Focused on performing a specific task or a narrow range of tasks. These
systems are designed to handle only particular problems and do not possess general intelligence.

Q15. What is the difference between AI,ML AND DL?

Artificial Intelligence Machine learning Deep Learning

The term Artificial The term ML was first coined The term DL was first coined
intelligence was first coined in the year 1959 by Arthur in the year 2000 Igor
in the year 1956 by John Samuel. Aizenberg.
McCarthy.

It is a technology that is used It is a subset of AI that learns It is the subset of machine

to create intelligent machines from past data and learning and AI that is
that can mimic human experiences. inspired by the human brain
behavior. cells, called neurons, and
imitates the working of the
human brain.

AI completely deals with ML deals with structured and Deep learning deals with
structured, semi-structured semi-structured data. structured and unstructured
data. data.
 It requires a huge amount of It can work with less amount It requires a huge amount of
data to work. of data compared to deep the data compared to the ML.
learning and AI.

The goal of AI is to enable The goal of ML is to enable The goal of deep learning is
the machine to think without the machine to learn from to solve complex problems as
any human intervention. past experiences. the human brain does, using
various algorithms.

Q16. What are the different platforms for Artificial Intelligence (AI) development?

● TensorFlow: An open-source machine learning framework developed by Google.

● PyTorch: An open-source machine learning library developed by Facebook, known for
its flexibility and ease of use.
● Keras: A high-level neural networks API that can run on top of TensorFlow, Theano, or
CNTK.
● Microsoft Azure AI: A suite of AI services and tools offered by Microsoft.
● Google Cloud AI: AI and machine learning services provided by Google Cloud.
● IBM Watson: A suite of AI tools and applications developed by IBM.
● Amazon SageMaker: A fully managed service by AWS for building, training, and
deploying machine learning models.
● H2O.ai: An open-source platform for AI and machine learning.
● RapidMiner: A data science platform that provides an integrated environment for data
preparation, machine learning, deep learning, and predictive analytics.

Q17.What is a Language Model in Natural Language Processing?

A language model in natural language processing (NLP) is a statistical or machine learning
model that is used to predict the next word in a sequence given the previous words. Language
models play a crucial role in various NLP tasks such as machine translation, speech recognition,
text generation, and sentiment analysis. They analyze and understand the structure and use of
human language, enabling machines to process and generate text that is contextually appropriate
and coherent.
Q18.What is a Heuristic Search?
A heuristic search is a strategy used in AI to optimize the search process by using a heuristic
function to estimate the cost of reaching a goal. Instead of exhaustively exploring all possible
paths, a heuristic search uses this estimate to prioritize the most promising paths, reducing
computational complexity and speeding up decision-making.
The heuristic function in AI acts as a guide, providing approximate solutions when exact answers
are computationally expensive or unnecessary. By leveraging domain-specific knowledge,
heuristic searches can solve real-world problems more efficiently than traditional methods.

Q19.What is Markov's Decision process?

The solution for a reinforcement learning problem can be achieved using the Markov decision
process or MDP. Hence, MDP is used to formalize the RL problem. It can be said as the
mathematical approach to solve a reinforcement learning problem. The main aim of this process is to
gain maximum positive rewards by choosing the optimum policy.

MDP has four elements, which are:

○ A set of finite states S

○ A set of finite actions A
○ Rewards
○ Policy Pa

Q20 Explain the Hidden Markov model.

The Hidden Markov model is a statistical model used for representing the probability distributions
over a chain of observations. In the hidden markov model, hidden defines a property that it assumes
that the state of a process generated at a particular time is hidden from the observer, and Markov
defines that it assumes that the process satisfies the Markov property. The HMM models are mostly
used for temporal data.

The HMM is used in various applications such as reinforcement learning, temporal pattern
recognition, etc.