Notes
of Coursera-MachineLearning-Andrew NG
Week1-2014/03/07-hphp
Machine Learning
Introduction
- Many
Application
- Amazon , Netflix
recommend system
- Arthur Samuel, made a machine learn how to
check. checkers , made
a program play chess with itself , and know better of how to win
.
- Popular
- and well .. currently large demands
of talents. as one of the top
12 computer skill
- Different types of
learning algorithms
- famous partial methods
: supervised learning ,
unsupervised learning,
- Main Goal
- how to develop the best
machine learning systems to get better performance.
Supervise
learning
how
to pick a model ? straight line or polynomial
?
- Regression:
Predict continous valued output
- Classification
problem ,
- tumor size Vs
malignant
- Tumor size ,
age , Vs malignant or benign ,
- could
use more features to predict ( or regression ) : uniformity of cell shape ,
cell size ......
- Statistically
- compromized :
妥协的
Unsupervised
Learning?
- clustering
problem
- google news ,
with one news , several diff urls are laid.
- astronomical
data analysis
- Cocktail party
problem
- seperate voice
source
- use
octave , could solve the problem quickly and briefly
Linear Regression with
one variable
Training
set : m : number of training examples , x : input , y : output
variable ,
y = h(x) , h
: hypothesis
How do we represent
H?
htheta(x) = theta0 +
theta1(x)
univariant -- linear
regression (a fancy name)
htheta(x) = theta0 +
theta1(x)
how to choose two
theta s
choose thetas so that
h(x) is close to given
examples.
m
minimize
= 1/2m Sum ( h(xi) - yi
) 2
theta0, theta 1
1
squared error function -- the most
common coss function in regression
.
- Cost function
intuition I - lecture 7
get
better intuition what cost function is doing , and why we want to use
it.
recap : focus , say
briefly
simplified : theta 0
= 0
h(x) = theta1 *
x
J(theta1) =
1/2m * Sum[i:1-m](theta1xi - yi) 2
when theta1 = 1
, J
( theta1 ) = 0
theta1 = 0.5 , J (
theta1 ) = 0.5 , J ( 0 ) =
14/6
- Cost
function intuition II - lecture 8
basic situation
- contour
plots : outline
- theta0,
theta1 != (0, x) or (x, 0) , with the cost function act as a 3D bowl ,
below
- using : contour plots (
or contour figures ) .
? using such data , and such model , we could see
that there a circle of "similar" point pairs of ( theta0, theta1)
,
on which they act the same, so , can we tell
the difference of different pairs ?
- Gradient
descent algorithm
- it
is used all over machine learning
- could
minimizing arbitrary functions besides cost function
- Basic
Thoughts
MachineLearning,布布扣,bubuko.com
MachineLearning
原文：http://www.cnblogs.com/hphp/p/3587255.html
- surface
->
VS 
