AI Tools and Techniques - Unit I & II
Detailed Notes
UNIT I: Introduction to AI
Definition of Artificial Intelligence (AI)
Artificial Intelligence (AI) is a branch of computer science that aims to create machines
capable of mimicking human intelligence. These intelligent systems can perform tasks such
as learning, reasoning, problem-solving, understanding language, and perceiving the
environment.
Problem in AI
A problem in AI consists of an initial state, goal state, set of actions, transition model, and
path cost function. AI systems solve problems by searching through possible states using
various techniques to find a solution path from the initial state to the goal.
State Space Representation
State space representation is a formal method of modeling a problem. It consists of all
possible states and transitions between states defined by actions. This representation is
typically visualized using a search tree or graph.
Intelligent Systems
Intelligent systems are those that can perceive their environment, process information, and
make decisions to achieve specified goals. Examples include expert systems, autonomous
vehicles, chatbots, and robotics.
Categorization of Intelligent Systems
1. Reactive Machines: No memory, respond to current input.
2. Limited Memory: Use historical data for decisions.
3. Theory of Mind: Understand emotions and thoughts (hypothetical).
4. Self-aware Systems: Possess consciousness and self-awareness (theoretical).
Components of AI Program
1. Knowledge Base: Stores facts and rules.
2. Inference Engine: Applies logic to derive conclusions.
3. Learning Module: Learns from data and improves over time.
4. Interface Module: Communicates with users/environment.
Foundations of AI
AI draws knowledge from several disciplines: mathematics (logic and probability),
computer science, cognitive science, neuroscience, linguistics, and philosophy.
Applications of AI
AI is widely used in robotics, natural language processing (NLP), expert systems, computer
vision, game playing, autonomous vehicles, and healthcare diagnostics.
Current Trends in AI
Emerging trends in AI include deep learning, generative AI (e.g., ChatGPT), reinforcement
learning, AI in IoT, AI for cybersecurity, and edge AI.
Intelligent Agents
An intelligent agent perceives its environment through sensors and acts upon it using
actuators. It has a performance measure that evaluates success.
Anatomy and Structure of Agents
An agent's structure consists of:
- Agent Function: Maps percepts to actions.
- Agent Architecture: The computational framework implementing the function.
Types of Agents
1. Simple Reflex Agents: Act on current percept.
2. Model-based Reflex Agents: Use internal state to track the world.
3. Goal-based Agents: Act to achieve goals.
4. Utility-based Agents: Maximize a utility function.
5. Learning Agents: Improve with experience.
