AI (CIE IGCSE Computer Science)

• Artificial Intelligence is a branch of computer science that involves creating computer systems that can perform tasks that would normally require human intelligence
• The goal of AI is to simulate intelligent behaviour in machines, including:
• problem-solving, decision-making, natural language processing
• AI is often used in areas such as:
• Robotics
• Natural language processing
• Expert systems
• Machine learning
• Machine learning is a subset of AI that focuses on giving computers the ability to learn and improve from data, without being explicitly programmed
• There are different types of AI, including weak AI, strong AI, and superintelligence
• Weak AI, also known as narrow AI, is designed to perform a specific task or set of tasks
• Strong AI, also known as artificial general intelligence (AGI), is designed to perform any intellectual task that a human can do
• Superintelligence is a hypothetical AI that would surpass human intelligence in all areas
• AI has advantages such as increased efficiency, accuracy, and scalability
• However, AI also has disadvantages such as the potential for job loss, biassed decision-making, and ethical concerns around its use

• Collection of data and rules
  • AI systems require large amounts of data to perform tasks
  • The data is processed using rules or algorithms that enable the system to make decisions and predictions
• Ability to reason
  • AI systems can use  logical reasoning  to evaluate information and make decisions based on that information
• Ability to learn and adapt
  • This will mean it can change its own rules and data

AI systems can be designed to learn from past experiences and adjust their behaviour accordingly

There are two main types of AI systems: 

Expert Systems:

• Have a knowledge base
• A database of facts to generate rules that are used to solve problems and make decisions
• Have a rule base
• A set of rules or logic that is used to apply the knowledge in the knowledge base to specific problems
• Have an inference engine
• A program that applies the rules in the rule base to the facts in the knowledge base to solve problems
• Have an interface
• A way for users to interact with the system and provide input

Machine Learning:

• The program has the ability to automatically adapt its own processes and/or data
• Uses algorithms to analyse data and identify patterns or relationships
• The system can learn from the data and improve its performance over time
• Can be supervised or unsupervised: 
• Supervised machine learning uses labelled data to train the system
• Unsupervised machine learning uses unlabelled data