1. What is Intelligence?
Discuss the idea behind
Artificial Intelligence.
Intelligence is the ability of an entity to learn from experience, adapt to new situations, understand
complex ideas, reason logically and solve problems. Human intelligence involves perception,
memory, language understanding and decision making.
Artificial Intelligence (AI) aims to design machines that can mimic human cognitive abilities. The
main idea behind AI is to make computers capable of performing tasks that normally require human
intelligence.
• Learning from data (Machine Learning)
• Reasoning and problem solving
• Perception such as vision and speech recognition
• Understanding natural language
• Decision making under uncertainty
AI combines computer science, mathematics, psychology and neuroscience to create intelligent
systems. Modern AI systems are used in virtual assistants, recommendation systems, medical
diagnosis and autonomous vehicles.
2. What is the Turing Test? Discuss various
categories of AI-based systems.
The Turing Test, proposed by Alan Turing in 1950, is a method to evaluate whether a machine can
exhibit human-like intelligence. If a human evaluator cannot distinguish between responses from a
human and a machine, the machine is considered intelligent.
Categories of AI systems:
• Reactive Machines – No memory, respond only to current input (e.g., chess playing computers)
• Limited Memory – Learn from past data (self-driving cars)
• Theory of Mind – Understand emotions and beliefs (under research)
• Self-Aware AI – Hypothetical machines with consciousness
AI systems can also be classified as Narrow AI, General AI and Super AI depending on capability.
3. Discuss the evolution of AI through various
generations.
1950–1970: Symbolic AI – Rule-based reasoning and logic systems
1980–1990: Expert Systems – Knowledge bases and inference engines used in medical and
industrial domains
1990–2010: Machine Learning – Algorithms learn patterns from datasets
2010–Present: Deep Learning – Neural networks with multiple layers performing speech, image
and language tasks
Future: General AI – systems capable of human-level reasoning across domains
4. What is an agent? Describe the Intelligent agent
and its structure.
An agent is anything that perceives its environment through sensors and acts upon it using
actuators.
An Intelligent Agent selects actions that maximize performance based on perception and
knowledge.
• Sensors – collect data from environment
• Actuators – perform actions
• Agent function – mapping percept to action
• Performance measure – evaluates success
Types include simple reflex agents, model-based agents, goal-based agents and learning agents.
5. Discuss the benefits of Computer Vision in
detail.
Computer Vision enables machines to interpret visual data from images and videos.
• Medical diagnosis from X-rays and MRI scans
• Autonomous driving object detection
• Face recognition security systems
• Quality inspection in industries
• Agriculture crop monitoring
• Retail cashier-less stores
It increases accuracy, reduces human effort and allows automation of visual tasks.
6. Explain the concept of Natural Language
Processing in detail.
NLP enables computers to understand, interpret and generate human language.
• Speech recognition
• Machine translation
• Chatbots and virtual assistants
• Sentiment analysis
• Text summarization
NLP uses tokenization, parsing, semantic analysis and deep learning models like transformers.
7. Differentiate between Informed and Uninformed
search with examples.
Uninformed search uses no additional knowledge. Example: Breadth First Search, Depth First
Search.
Informed search uses heuristics to guide search. Example: A* algorithm, Greedy Best First Search.
Informed search is faster and more efficient because it estimates distance to goal.
8. Explain the problems in the Hill climbing
algorithm. Why is it considered a local search
algorithm?
Hill climbing is an optimization algorithm that moves toward better states.
• Local maxima problem
• Plateau problem
• Ridge problem
It is called local search because it considers only neighboring states rather than the entire search
space.
9. Differentiate between the Min Max algorithm and
alpha-beta pruning.
Minimax evaluates all nodes in a game tree to select optimal move.
Alpha-beta pruning eliminates branches that cannot affect final decision.
• Minimax is slower
• Alpha-beta pruning improves efficiency
• Both used in adversarial games like chess