Machine Learning
- This is the area that I currently research.
- I heard Bill Gates once say (a couple of years ago) that
AI is now called Machine Learning.
- While I think Bill is wrong here, it points out the importance
of learning.
- The way I think about data mining is it's just machine
learing with smart use of data base technology.
- The point in the first page of this talk was that computers are good at
processing a lot of data quickly.
- If a computer can look through a lot of data quickly, and learn
some new things from that data, then it might do something really
useful.
- It's not that most learning techniques are particularly advanced,
it's that they're fast.
- There are a lot of learning techniques including fuzzy systems
and ad hoc mechanisms. We'll drill down into these:
- Statistics
- Rule Induction
- Connectionist Systems
- Genetic Algorithms
- Neural Networks
- The journal of machine learning is not a bad place to start on
this. Artificial Intelligence (the Elsevier journal) is the
seminal journal, but its scope is wider than machine learning.
