Machine Learning Notes

this is the summary: courses of ML on

cousera

by Andrew Ng

1.What is Machine Learning?

**Definition:**A computer program is said to learn from experience E with respect to some tasks T and some performance measure P,if its performance on T,as measured by P,improves with experience E.

E

:test data,learning process

P

:the evaluation/summary of learning,prediction by this program is accuracy/correct or not.

T

:The goal we want to achieve.

2.Classification

• Supervised Learning

  Given the right/exact anwser for each example in the data.

  • Regresstion: estimate the relationships among variables with continuous output.
  • Classification: identify which category an example belongs to with discrete output.

• Unsupervised Learning

  allow us to approach problems with little or no idea what our results should like.

3.Model Representation

a training set

–

learning algorithm

–>

h

(hypothesis)

After that, we use this

h

to predict

y

with

x

4.Cost Function

What you should always keep in mind is that function J is parametered by theta rather than

x

or

y

.

5.Gradient Descent

We have put forward the goal we are going to do: minimize the function J.

BUT how to achieve that?

There are two ways in linear regresstion.And now let’t introduce the first one: Gradient Descent

algorithm:

Attention: At each iteration,one should simutaneouly updata the parameters theta.

Batch gradient descent: this method looks at every example in the entire training set on every step.