NG Machine Learning -Lecture01
<p>Nov 19, 2009 8:52 PM
 
1959  Art Samuel  checkers program.  was self-taught and could beat him.
 
Here's a more recent, a more modern, more formal definition of machine learning due to
Tom Mitchell, who says that a well-posed learning problem is defined as follows: He
says that a computer program is set to <b>learn from an experience E with respect to some
task T and some performance measure P if its performance on T as measured by P
improves with experience E. Okay. So not only is it a definition, it even rhymes.  </b>
 
 
SUPERVISED LEARNING
 
    REgression of  HOUSES:  square footage, sales price.
You supply it with the right answer... the sale sprice.
 
 
 
    Breat Cancer classification vs benign tumors:  X or O  based
on a # of diftt variables.
 
Support VECTOR Machines.
 
A learning theorem for reading zip codes ... can prove that it will be 99.9 % accurate.</p>