Please enable JavaScript.
Coggle requires JavaScript to display documents.
AI METHODS - Coggle Diagram
AI METHODS
Machine learning
Traditional programming
You write an algorithm (Step by step instructions)
The computer follows the command exactly
Machine learning
You don't write an algorithm.
The computer learns how to solve the problem on its own.
It finds patterns in the data
It gorups similar images or data together
The computer is given a lot of organized and labeled data.
Neutral networks
A structure that combines all learning methods
Feedback
Tells the computer if it’s moving toward the right goal.
It requires a large amount of diverse and varied data
You don't need to tell the computer how to solve the problem
Applications
Diagnosing illnesses
Weather forecasting
Recognising signs of hurricanes
Expert system
Its components are inputs, processes, structure and outputs
It will output a decision that matenes what the human would decide
It is an algoirthm that represents the knowledge of an expert
It will always make decisions without bias or favour
It will take all the factors that a human would consider
Heuristcs
It is a rule that helps you make a quick decision
They provide a quick way to simplify difficult problems
They help computers to make human-like decisions
Decision trees
It is a way of setting out the logical tests
You can easily find answers to qquestions
It can be automated by turning it into a program