Introduction to Artificial Intelligence Lecture Notes

Comprehensive vocabulary terms and concepts covering the basics of AI, its domains, project life cycles, and categories of learning.

Artificial Intelligence (AI)

The ability of a machine to perform various tasks that require human intelligence by mimicking human cognitive processes.

Human Intelligence

Intelligence possessed by birth or nature that learns by experience and uses food as fuel.

Artificial Intelligence Fuel

Data is the fuel used by AI systems to learn and function.

Computer Vision (CV)

An AI domain involving the ability of a machine to understand and interpret input visual information, such as face recognition systems.

Natural Language Processing (NLP)

An AI domain involving the ability to understand, interpret, and respond to human language meaningfully, like Alexa or Siri.

Statistical Data (SD)

An AI domain focused on the ability of a machine to identify patterns, trends, and relationships in large datasets, used in data science and analytics.

AI Learning Process

AI systems are designed to learn, improve, and adapt their performance over time through data training and pattern recognition.

Project

A series or structure of tasks and activities performed to achieve a specific result.

AI Project

A step-by-step process of developing a smart system to solve a real-world problem by learning from data.

AI Project Life Cycle

An interactive six-stage framework for developing, deploying, and maintaining AI tools.

Identify & define the goal

The first stage of the AI life cycle, focused on problem solving.

Data Acquisition

The second stage of the AI life cycle, involving the collection and preparation of clean data.

Data Exploration

The third stage of the AI life cycle, involving the building and training of AI models.

Modelling & Testing

The fourth stage of the AI life cycle, used to test and access performance.

Deployment

The fifth stage of the AI life cycle, where the system is displayed in the real world.

Monitoring & Maintenance

The final stage of the AI life cycle, involving tracking and performance maintenance.

Machine Learning (ML)

A field of AI where computers learn from data and improve their performance without being directly programmed for every task.

Supervised Learning

A type of machine learning where the system learns with the help of labelled data.

Unsupervised Learning

A type of machine learning where the system learns with unlabelled data and finds patterns on its own.

Reinforcement Learning

A type of machine learning where the system learns by trial and error and receives rewards for correct actions.

Deep Learning

A field of AI where computers learn using many layers of a neural or neuro network, such as in self-driving cars.

Robotics

A field of AI focused on designing and using machines that can perform tasks automatically or with little human help.

Expert Systems

A field of AI where computers are designed to think and make decisions like a human expert in a specific area, such as medical diagnosis programs.

Automation

A system that follows fixed rules to perform tasks automatically without learning from data, such as an automatic car wash system.

AI based Car Wash

A system that replaces fixed rules with AI, using cameras to detect car size and dirt levels to decide water spray times and soap usage.