【Machine Learning】Supervised Learning
Concept:
Supervised learning(监督学习) is to tell the algorithm what the close right answer is for a number of examples,and then we want the algorithm to replicate more or the same.
Part I Liner Regression(线性回归)
Liner function(线性函数):
cost funtion(成本函数):
When is minimization,the is optimal solution.
Part II LMS(Least mean squares) Algorithm Iterative method
We use gradient descent algorithm to choose .
Search function:
(for every j)
Frist, we use it that starts with some "initial guess" for , and that repeatedly change to make smaller,until hopefully we converge to a value of that minimizes .
Use one training example (x,y), we can infer that
So, for a single training example, the update rule is:
For m training sample, the update rule is:
Repeat until convergence {
(for every j)
}
This is called batch gradient descent.
But, if m is large, batch gradient descent has to scan through the entire training set before taking a single step. It's a costly operation.
Stochastic gradient descent can deal with it.
for i=1 to m, {
(for every j)
}
But the accuracy of this algorithm is lower than former.
Part III Normal Equations
1、Matrix derivatives (矩阵导数)
2、Trace Operator: