Professional Documents
Culture Documents
AIMLQuestion Bank
AIMLQuestion Bank
2. Provide a chronological account of the History of AI spanning from 1950 to the present day.
5. Identify two types of AI problems and elucidate the components of well-defined problems.
8. Define the concept of an environment and elucidate different types of environments with suitable
examples.
9. Discuss the goals of AI, detailing seven steps with illustrative examples.
10. Clarify distinctions between Hard and Soft AI, Soft and Weak AI, as well as Narrow and General
AI.
11. Define an Agent, using figures to illustrate the concept and its interrelationship with the
environment.
13. Identify different search strategies, highlighting the importance of four key parameters.
14. Explain uninformed strategies, detailing their types and providing examples for better
comprehension.
17. Explain the concept of Constraint Satisfaction Problems, offering a relevant example.
19. Outline the steps involved in Natural Language Processing (NLP) and explain its two distinct
components.
20. Define computer vision and explore its diverse applications in real-world scenarios.
21. What do you mean by propositional Logic? Explain its logic with its truth table and provide
examples.
1. Define Artificial Intelligence and illustrate its Block Diagram highlighting
various AI domains.
1960
AI attempts to move beyond toy domains.
Syntactic knowledge alone does not work, domain knowledge required.
Earliest expert system created: Dendral
1970
AI researchers address real-world problems and solutions through expert
(knowledge-based) systems:
Medical diagnosis, Speech recognition, Planning, Design.
Uncertainty handling implemented:
Fuzzy logic, Certainty factors, Bayesian probabilities
AI begins to get noticed due to these successes
o AI research
o AI labs
o AI shells
o AI machines
1980s: AI Winter
Funding dries up leading to the AI Winter
◦ Too many expectations were not met.
◦ Expert systems took too long to develop, too much money to
invest, the results did not pay off.
1990 A Life
By their own admission, AI researchers are not doing “AI”, they are
doing:
o Intelligent agents, multi-agent systems/collaboration
o Ontologies
o Machine learning and data mining
o Adaptive and perceptual systems
o Robotics, path planning
o Search engines, filtering, recommendation systems
Advantages:
◦ More powerful and more useful computers
◦ New and improved interfaces
◦ Solving new problems
◦ Better handling of information
◦ Relieves information overload
◦ Conversion of information into knowledge
Disadvantages:
◦ Increased costs
◦ Difficulty with software development - slow and expensive
◦ Few experienced programmers
◦ Few practical products have reached the market yet.
5. Identify two types of AI problems and elucidate the components of well-
defined problems.
Types of Problem
1) When the environment is completely accessible and the agent can calculate
its state after any sequence of action, we call it a single-state problem.
2) When the world is not fully accessible, the agent must reason about sets of
states that it might get to, rather than single states. We call this a multiple-
state problem.
Components of Well-Defined AI Problems:
1. Clear Objective:
Definition: The problem that the AI system is supposed to solve must be clearly
defined. It could be anything from recognizing objects in images to playing a
game.
Example: Recognize handwritten digits in images.
2. Quality Data:
Definition: High-quality, relevant data is essential for training AI models. The
data should be representative of the problem domain.
Example: A dataset of labelled handwritten digits with corresponding images
for training a digit recognition model.
3. Feature Selection:
Definition: Features are the variables or attributes used by the AI system to
make predictions or decisions. Selecting relevant features is crucial for the
system's performance.
Example: Pixel values in an image can be features for image recognition tasks.
4. Algorithms/Models:
Definition: AI algorithms or models process the input data and generate
predictions or decisions. Choosing an appropriate algorithm/model is vital for
the success of the AI system.
Example: Convolutional Neural Networks (CNNs) for image recognition tasks.
5. Training:
Definition: Training involves using the algorithm/model to learn from the input
data (with known outcomes) to make predictions or decisions.
Example: Training a CNN using the labeled dataset of handwritten digits to
recognize new, unseen digits.
3. Facilitate planning
Intelligent agents provide a way to envision the future. AI-driven
planning determines a procedural course of action for a system to
achieve its goals and optimizes overall performance through predictive
analytics, data analysis, forecasting, and optimization models.
With the help of AI, we can make future predictions and ascertain the
consequences of our actions. Planning is relevant across robotics,
autonomous systems, cognitive assistants, and cybersecurity.
4. Allow continuous learning
6. Promote creativity
Hard AI Soft AI
2) Narrow AI vs General AI