Introduction to Artificial Intelligence (AI)

Introduction to Artificial Intelligence

• Artificial Intelligence (AI) is a technique that enables systems to mimic human behavior.
• AI refers to computer systems capable of performing complex tasks that historically only a human could do; such as reasoning, making decisions, or solving problems.
• AI is an umbrella term that encompasses several technologies, including machine learning, deep learning, and natural language processing (NLP).

History of AI

• The term "Artificial Intelligence" was first adopted by American Computer scientist John McCarthy at the Dartmouth Conference.
• The period from 1956 to 1974 is known as the "Golden Age" of artificial intelligence (AI).
• Between 1993 and 2011, there were significant advances in AI, particularly in developing intelligent computer programs.
• From 2011 to the present, significant advancements have unfolded within the AI domain.

Why AI is Important

• AI can process and analyze vast amounts of data faster than humans.
• AI uses data to forecast outcomes with high precision.
• AI tailors recommendations based on individual preferences.
• AI offers data-driven insights to make informed choices.
• AI helps create software/ devices that solve real-world problems with accuracy like health and traffic issues.
• AI opens a path for other technologies, devices, and opportunities.

AI in Everyday Life

• ChatGPT uses large language models (LLMs) to generate text in response to questions or comments.
• Google Translate utilizes deep learning algorithms to translate text from one language to another.
• Netflix uses machine learning algorithms to create personalized recommendation engines for users based on their viewing history.
• Tesla uses computer vision to power self-driving features in its cars.

Types of Artificial Intelligence

• Narrow AI (Weak AI) is designed to perform a specific task, like facial recognition or virtual assistants like Siri/Alexa, and cannot perform tasks beyond its programmed function.
• General AI (AGI - Artificial General Intelligence) can understand, learn, and apply intelligence across a wide range of tasks, similar to human intelligence, but is theoretical and not yet developed.
• Superintelligent AI is a hypothetical AI that surpasses human intelligence in every aspect and is speculative and not yet realized.

Intelligent Agents

• An intelligent agent is a program that can make decisions or perform a service based on its environment, user input, and experiences.
• These programs can gather info autonomously in real time.

Key Components of Intelligent Agents:

• Perception (Sensors): The agent perceives its environment through physical sensors like cameras/microphones, or virtual sensors like input from a website/software.
• Decision-Making: The agent processes, analyzes, and decides the best course of action, often involving algorithms like machine learning or rule-based systems.
• Actions (Effectors/Actuators): The agent takes action, for example; moving a robotic arm, sending a message, or updating a software process.
• Examples include virtual assistants like Siri/Alexa and robot vacuum cleaners.

Rules for AI Agents

• Rule 1: An AI agent must have the ability to perceive the environment.
• Rule 2: The observation must be used to make decisions.
• Rule 3: Decision should result in an action.
• Rule 4: The action taken by an AI agent must be a rational action.

Components of Intelligent Agents

• Sensors (Perception) gather information from the environment; examples are cameras, microphones, GPS, and temperature sensors.
• Actuators (Action) execute actions to influence the environment; examples include motors, speakers, displays, and robotic arms.
• Decision-Making (Processing) involves analyzing data, making choices, and determining the best course of action; examples are algorithms, decision trees, and machine learning models.
• Learning Mechanism (Adaptation) improves performance over time by learning from past experiences; examples are reinforcement learning, supervised learning, and neural networks.

PEAS Representation

• Performance: Safety, time, legal drive, comfort
• Environment: Roads, other vehicles, road signs, pedestrian
• Actuators: Steering, accelerator, brake, signal, horn
• Sensors: Camera, GPS, speedometer, odometer, accelerometer, sonar.

Types of Intelligent Agents:

• Simple Reflex Agents react directly to specific inputs using set rules, for example, a smoke detector.
• Model-Based Agents use an internal model to understand and react to the environment, for example, a robot using a map to navigate.
• Goal-Based Agents make decisions to achieve specific goals, for example, a GPS navigation system.
• Utility-Based Agents choose actions to maximize overall satisfaction or benefit, for example, a movie recommendation system.