6.3 Artificial intelligence

AI is a branch of computer science dealing with the simulation of intelligent behaviors by computers. AI Can learn, decide and act autonomously.
Types:

• Weak AI/Narrow AI: Performs specific task or tasks
• Strong AI/Artificial general intelligence (AGI): Performs intellectual task like human

Characteristics

• Collection of data and the rules for using that data: Ai needs huge data sets to operate and perform tasks. Data is collected from various sources like text, image, sensors, human interactions. These data are then processed using a rule that enables the system to form decisions
• Ability to reason: AI can make decisions, solve problems, and draw conclusions based on data patterns.
• Ability to learn and adapt: AI learns from past experiences, adapting its responses over time to improve performance in changing environments.

Expert System

• Mimics human knowledge and experience to solve problems
• Examples: Medical diagnosis system, tech support, chatbots, equipment troubleshooting, financial calculations
• Expert system consists of
  • Knowledge Base: Stores facts and information relevant to the expert system's domain to solve problem and make decisions
  • Rule Base: Contains rules and logic that guide decision-making based on the knowledge base
  • Inference Engine: Program applying the rules of the rule base to the facts in the knowledge base to solve problems
  • Interface: Allows users to interact with the expert system and receive insights
• Advantages: Consistent result, faster, large storage, not biased
• Disadvantage: Quality depends on data enter, responses lack emotion, training required for proper use

Machine Learning

• When a program has the ability to automatically adapt its own processes and/or data.
• Uses different algorithm to search data and identify patterns
• It can edit its own data
• Results are stored to influence future decisions
• It can be trained in the following methods
  • Supervised: With human interaction, meaning user tells the system the input and output
  • Unsupervised: Without much human interaction, meaning user gives the input and the AI needs to work out the output

Difference Between AI and Machine Learning