Please enable JavaScript.
Coggle requires JavaScript to display documents.
Methods computers use to solve problems - Coggle Diagram
Methods computers use to solve problems
Heuristics
is a rule that helps people make a quick decision
advantages
makes work easier for the user
they give a good-enough result
can solve problems quite quickly
disadvantages
The solution provided might not be the best one
can produce some incorrect results
They are not always completely accurate
Machine learning
advantages
do not have to tell the computer how to solve the problem
the computer is given a goal and it will work out its own solution
disadvantages
data must be diverse and varied
can go wrong
the computer needs a lot of data
uses
weather forecasting
understanding speech
diagnosing illnesses
spotting computer viruses
recognise faces and make images of faces
it is different from an algorythm
the computer has to learn how to solve a problem for itself
training the computer
unsupervised traning
reinforcement learning
supervised training
data has already been organised and labelled, the computer will tell the diference between them.(faces and other images)
deep learning
can produce very powerful results
it uses a computer structure called neural network
Decision trees
can be used to find aswers to questions
Expert systems
is an algorithm that represents the knowledge of an expert
advantages
The rules are in the code, so fairness can be verified
An expert system can be used when a human isn't available
It consistently makes unbiased decisions
disadvantages
Experts may struggle to articulate their skills.
Not everything fits into logical tests.
If experts are wrong, the algorithm will be wrong too.