Skip to content

HTTPS clone URL

Subversion checkout URL

You can clone with
or
.
Download ZIP
Browse files

To Cost Function Intuition 1

  • Loading branch information...
commit fe45a2005c58790bf251f4b48e1f27bec0288e9a 1 parent c9eaf96
@jneira jneira authored
Showing with 39 additions and 0 deletions.
  1. +39 −0 2.-Linear_regression_with_one_variable/notes.org
View
39 2.-Linear_regression_with_one_variable/notes.org
@@ -0,0 +1,39 @@
+* Model Representation
+ - Supervised Learning:
+ - Given the "right answer" for each example in the data.
+ - Regression Problem:
+ - Predict real-values output
+ - Data set is called "Training set"
+ - Notation:
+ - m = Number of training examples
+ - x's = "input" variable/features
+ - y's = "output" variable/"target" variable
+ - (x,y) = one training example
+ - (x[i],y[i]) = i^th training example
+ - Model:
+ x
+ |
+ Training Set --> Learning Algorithm --> /h/ (hypothesis)
+ |
+ y
+ h: function x->y
+
+ - How do we represent h? *as a linear function*
+ - h[Θ](x) = Θ[0]+Θ[1]x Shorthand: h(x)
+ - To start with a simple building block
+ - Model name:
+ - Linear regression with one variable.
+ - aka Univariate linear regression.
+
+* Cost function
+ - How to choose Θ[i]'s parameters in hypothesis
+ - Idea: choose Θ[0],Θ[1] so that hΘ(x) is close to /y/ for our
+ training examples (x,y)
+ - Formalization:
+ - minimize J(Θ[1],Θ[2])=1/2m Σ(i=1..m)(h[Θ](x^(i))- y^(i))^2
+ - h[Θ](x^(i))=Θ[0]+Θ[1]x^(i)
+ - choose values for Θ[0],Θ[1] that minimez the function
+ - m -> #training examples
+ - squared error cost function
+
+* Cost function - Intuition I
Please sign in to comment.
Something went wrong with that request. Please try again.