Scribd
Upload
6 views

MLT OPPE Formula Guide

Uploaded by

Adavya
Copyright
© © All Rights Reserved
Available Formats
Download as PDF, TXT or read online on Scribd
6 views

MLT OPPE Formula Guide

Uploaded by

Adavya
Copyright
© © All Rights Reserved
Available Formats
Download as PDF, TXT or read online on Scribd
You are on page 1/ 2

MLT OPPE Formula Guide

Regression
Normal Equation Linear Regression
T −1
w = (XX ) XY

^ = wT X
y

Gradient Descent
t+1 t t T t
w = w − η (2XX w − 2XY )

^ = wT X
y

Stochastic Gradient Descent


Same formula as Gradient Descent, except that X and y are random samples of the
whole dataset.

Kernel Regression
T degree
K = (X X + 1)

−1
α = K y

^ = KTα
y

Ridge Regression
T −1
w ridge = (XX + λI ) XY

Error
1 n 2
RM SE = √ ∑ (y − y)
^
n i=1

SVM
Objective Function
min f (α)
α>=0

Where

1
∗ T T
f (α) = α = ⋅ α Qα − α 1
2

T T
Q = Y X XY

Equation of Decision Boundary


−w 0
y = x db
w1

Supporting Hyperplanes
1 w0
y = − ∗ x
w1 w1

And

1 w0
y = − − ∗ x
w1 w1

For soft margin SVM, make the Bounds of the optimization function as (0, C).

Perceptron
If sign(w T x i )! = yi for a data point:

w = w + xi yi

You might also like